Showing 1–50 of 206 results for author: Goel, A

Just Add Geometry: Gradient-Free Open-Vocabulary 3D Detection Without Human-in-the-Loop

Authors: Atharv Goel, Mehar Khurana

Abstract: Modern 3D object detection datasets are constrained by narrow class taxonomies and costly manual annotations, limiting their ability to scale to open-world settings. In contrast, 2D vision-language models trained on web-scale image-text pairs exhibit rich semantic understanding and support open-vocabulary detection via natural language prompts. In this work, we leverage the maturity and category d… ▽ More Modern 3D object detection datasets are constrained by narrow class taxonomies and costly manual annotations, limiting their ability to scale to open-world settings. In contrast, 2D vision-language models trained on web-scale image-text pairs exhibit rich semantic understanding and support open-vocabulary detection via natural language prompts. In this work, we leverage the maturity and category diversity of 2D foundation models to perform open-vocabulary 3D object detection without any human-annotated 3D labels. Our pipeline uses a 2D vision-language detector to generate text-conditioned proposals, which are segmented with SAM and back-projected into 3D using camera geometry and either LiDAR or monocular pseudo-depth. We introduce a geometric inflation strategy based on DBSCAN clustering and Rotating Calipers to infer 3D bounding boxes without training. To simulate adverse real-world conditions, we construct Pseudo-nuScenes, a fog-augmented, RGB-only variant of the nuScenes dataset. Experiments demonstrate that our method achieves competitive localization performance across multiple settings, including LiDAR-based and purely RGB-D inputs, all while remaining training-free and open-vocabulary. Our results highlight the untapped potential of 2D foundation models for scalable 3D perception. We open-source our code and resources at https://github.com/atharv0goel/open-world-3D-det. △ Less

Submitted 6 July, 2025; originally announced July 2025.

Audio Flamingo 3: Advancing Audio Intelligence with Fully Open Large Audio Language Models

Authors: Arushi Goel, Sreyan Ghosh, Jaehyeon Kim, Sonal Kumar, Zhifeng Kong, Sang-gil Lee, Chao-Han Huck Yang, Ramani Duraiswami, Dinesh Manocha, Rafael Valle, Bryan Catanzaro

Abstract: We present Audio Flamingo 3 (AF3), a fully open state-of-the-art (SOTA) large audio-language model that advances reasoning and understanding across speech, sound, and music. AF3 introduces: (i) AF-Whisper, a unified audio encoder trained using a novel strategy for joint representation learning across all 3 modalities of speech, sound, and music; (ii) flexible, on-demand thinking, allowing the mode… ▽ More We present Audio Flamingo 3 (AF3), a fully open state-of-the-art (SOTA) large audio-language model that advances reasoning and understanding across speech, sound, and music. AF3 introduces: (i) AF-Whisper, a unified audio encoder trained using a novel strategy for joint representation learning across all 3 modalities of speech, sound, and music; (ii) flexible, on-demand thinking, allowing the model to do chain-of-thought-type reasoning before answering; (iii) multi-turn, multi-audio chat; (iv) long audio understanding and reasoning (including speech) up to 10 minutes; and (v) voice-to-voice interaction. To enable these capabilities, we propose several large-scale training datasets curated using novel strategies, including AudioSkills-XL, LongAudio-XL, AF-Think, and AF-Chat, and train AF3 with a novel five-stage curriculum-based training strategy. Trained on only open-source audio data, AF3 achieves new SOTA results on over 20+ (long) audio understanding and reasoning benchmarks, surpassing both open-weight and closed-source models trained on much larger datasets. △ Less

Submitted 10 July, 2025; originally announced July 2025.

Comments: Code, Datasets and Models: https://research.nvidia.com/labs/adlr/AF3/

AI Space Cortex: An Experimental System for Future Era Space Exploration

Authors: Thomas Touma, Ersin Daş, Erica Tevere, Martin Feather, Ksenia Kolcio, Maurice Prather, Alberto Candela, Ashish Goel, Erik Kramer, Hari Nayar, Lorraine Fesq, Joel W. Burdick

Abstract: Our Robust, Explainable Autonomy for Scientific Icy Moon Operations (REASIMO) effort contributes to NASA's Concepts for Ocean worlds Life Detection Technology (COLDTech) program, which explores science platform technologies for ocean worlds such as Europa and Enceladus. Ocean world missions pose significant operational challenges. These include long communication lags, limited power, and lifetime… ▽ More Our Robust, Explainable Autonomy for Scientific Icy Moon Operations (REASIMO) effort contributes to NASA's Concepts for Ocean worlds Life Detection Technology (COLDTech) program, which explores science platform technologies for ocean worlds such as Europa and Enceladus. Ocean world missions pose significant operational challenges. These include long communication lags, limited power, and lifetime limitations caused by radiation damage and hostile conditions. Given these operational limitations, onboard autonomy will be vital for future Ocean world missions. Besides the management of nominal lander operations, onboard autonomy must react appropriately in the event of anomalies. Traditional spacecraft rely on a transition into 'safe-mode' in which non-essential components and subsystems are powered off to preserve safety and maintain communication with Earth. For a severely time-limited Ocean world mission, resolutions to these anomalies that can be executed without Earth-in-the-loop communication and associated delays are paramount for completion of the mission objectives and science goals. To address these challenges, the REASIMO effort aims to demonstrate a robust level of AI-assisted autonomy for such missions, including the ability to detect and recover from anomalies, and to perform missions based on pre-trained behaviors rather than hard-coded, predetermined logic like all prior space missions. We developed an AI-assisted, personality-driven, intelligent framework for control of an Ocean world mission by combining a mix of advanced technologies. To demonstrate the capabilities of the framework, we perform tests of autonomous sampling operations on a lander-manipulator testbed at the NASA Jet Propulsion Laboratory, approximating possible surface conditions such a mission might encounter. △ Less

Submitted 21 July, 2025; v1 submitted 9 July, 2025; originally announced July 2025.

Gemini 2.5: Pushing the Frontier with Advanced Reasoning, Multimodality, Long Context, and Next Generation Agentic Capabilities

Authors: Gheorghe Comanici, Eric Bieber, Mike Schaekermann, Ice Pasupat, Noveen Sachdeva, Inderjit Dhillon, Marcel Blistein, Ori Ram, Dan Zhang, Evan Rosen, Luke Marris, Sam Petulla, Colin Gaffney, Asaf Aharoni, Nathan Lintz, Tiago Cardal Pais, Henrik Jacobsson, Idan Szpektor, Nan-Jiang Jiang, Krishna Haridasan, Ahmed Omran, Nikunj Saunshi, Dara Bahri, Gaurav Mishra, Eric Chu , et al. (3284 additional authors not shown)

Abstract: In this report, we introduce the Gemini 2.X model family: Gemini 2.5 Pro and Gemini 2.5 Flash, as well as our earlier Gemini 2.0 Flash and Flash-Lite models. Gemini 2.5 Pro is our most capable model yet, achieving SoTA performance on frontier coding and reasoning benchmarks. In addition to its incredible coding and reasoning skills, Gemini 2.5 Pro is a thinking model that excels at multimodal unde… ▽ More In this report, we introduce the Gemini 2.X model family: Gemini 2.5 Pro and Gemini 2.5 Flash, as well as our earlier Gemini 2.0 Flash and Flash-Lite models. Gemini 2.5 Pro is our most capable model yet, achieving SoTA performance on frontier coding and reasoning benchmarks. In addition to its incredible coding and reasoning skills, Gemini 2.5 Pro is a thinking model that excels at multimodal understanding and it is now able to process up to 3 hours of video content. Its unique combination of long context, multimodal and reasoning capabilities can be combined to unlock new agentic workflows. Gemini 2.5 Flash provides excellent reasoning abilities at a fraction of the compute and latency requirements and Gemini 2.0 Flash and Flash-Lite provide high performance at low latency and cost. Taken together, the Gemini 2.X model generation spans the full Pareto frontier of model capability vs cost, allowing users to explore the boundaries of what is possible with complex agentic problem solving. △ Less

Submitted 22 July, 2025; v1 submitted 7 July, 2025; originally announced July 2025.

Comments: 72 pages, 17 figures

Learning hidden cascades via classification

Authors: Derrick Gilchrist Edward Manoharan, Anubha Goel, Alexandros Iosifidis, Henri Hansen, Juho Kanniainen

Abstract: The spreading dynamics in social networks are often studied under the assumption that individuals' statuses, whether informed or infected, are fully observable. However, in many real-world situations, such statuses remain unobservable, which is crucial for determining an individual's potential to further spread the infection. While this final status is hidden, intermediate indicators such as sympt… ▽ More The spreading dynamics in social networks are often studied under the assumption that individuals' statuses, whether informed or infected, are fully observable. However, in many real-world situations, such statuses remain unobservable, which is crucial for determining an individual's potential to further spread the infection. While this final status is hidden, intermediate indicators such as symptoms of infection are observable and provide important insights into the spread process. We propose a partial observability-aware Machine Learning framework to learn the characteristics of the spreading model. We term the method Distribution Classification, which utilizes the power of classifiers to infer the underlying transmission dynamics. We evaluate our method on two types of synthetic networks and extend the study to a real-world insider trading network. Results show that the method performs well, especially on complex networks with high cyclic connectivity, supporting its utility in analyzing real-world spreading phenomena where direct observation of individual statuses is not possible. △ Less

Submitted 12 June, 2025; v1 submitted 16 May, 2025; originally announced May 2025.

Visually Interpretable Subtask Reasoning for Visual Question Answering

Authors: Yu Cheng, Arushi Goel, Hakan Bilen

Abstract: Answering complex visual questions like `Which red furniture can be used for sitting?' requires multi-step reasoning, including object recognition, attribute filtering, and relational understanding. Recent work improves interpretability in multimodal large language models (MLLMs) by decomposing tasks into sub-task programs, but these methods are computationally expensive and less accurate due to p… ▽ More Answering complex visual questions like `Which red furniture can be used for sitting?' requires multi-step reasoning, including object recognition, attribute filtering, and relational understanding. Recent work improves interpretability in multimodal large language models (MLLMs) by decomposing tasks into sub-task programs, but these methods are computationally expensive and less accurate due to poor adaptation to target data. To address this, we introduce VISTAR (Visually Interpretable Subtask-Aware Reasoning Model), a subtask-driven training framework that enhances both interpretability and reasoning by generating textual and visual explanations within MLLMs. Instead of relying on external models, VISTAR fine-tunes MLLMs to produce structured Subtask-of-Thought rationales (step-by-step reasoning sequences). Experiments on two benchmarks show that VISTAR consistently improves reasoning accuracy while maintaining interpretability. Our code and dataset will be available at https://github.com/ChengJade/VISTAR. △ Less

Submitted 12 May, 2025; originally announced May 2025.

A4L: An Architecture for AI-Augmented Learning

Authors: Ashok Goel, Ploy Thajchayapong, Vrinda Nandan, Harshvardhan Sikka, Spencer Rugaber

Abstract: AI promises personalized learning and scalable education. As AI agents increasingly permeate education in support of teaching and learning, there is a critical and urgent need for data architectures for collecting and analyzing data on learning, and feeding the results back to teachers, learners, and the AI agents for personalization of learning at scale. At the National AI Institute for Adult Lea… ▽ More AI promises personalized learning and scalable education. As AI agents increasingly permeate education in support of teaching and learning, there is a critical and urgent need for data architectures for collecting and analyzing data on learning, and feeding the results back to teachers, learners, and the AI agents for personalization of learning at scale. At the National AI Institute for Adult Learning and Online Education, we are developing an Architecture for AI-Augmented Learning (A4L) for supporting adult learning through online education. We present the motivations, goals, requirements of the A4L architecture. We describe preliminary applications of A4L and discuss how it advances the goals of making learning more personalized and scalable. △ Less

Submitted 8 May, 2025; originally announced May 2025.

Comments: 14 pages, 7 figures

Proceedings of 1st Workshop on Advancing Artificial Intelligence through Theory of Mind

Authors: Mouad Abrini, Omri Abend, Dina Acklin, Henny Admoni, Gregor Aichinger, Nitay Alon, Zahra Ashktorab, Ashish Atreja, Moises Auron, Alexander Aufreiter, Raghav Awasthi, Soumya Banerjee, Joe M. Barnby, Rhea Basappa, Severin Bergsmann, Djallel Bouneffouf, Patrick Callaghan, Marc Cavazza, Thierry Chaminade, Sonia Chernova, Mohamed Chetouan, Moumita Choudhury, Axel Cleeremans, Jacek B. Cywinski, Fabio Cuzzolin , et al. (83 additional authors not shown)

Abstract: This volume includes a selection of papers presented at the Workshop on Advancing Artificial Intelligence through Theory of Mind held at AAAI 2025 in Philadelphia US on 3rd March 2025. The purpose of this volume is to provide an open access and curated anthology for the ToM and AI research community. This volume includes a selection of papers presented at the Workshop on Advancing Artificial Intelligence through Theory of Mind held at AAAI 2025 in Philadelphia US on 3rd March 2025. The purpose of this volume is to provide an open access and curated anthology for the ToM and AI research community. △ Less

Submitted 28 April, 2025; originally announced May 2025.

Comments: workshop proceedings

Improving the Reproducibility of Deep Learning Software: An Initial Investigation through a Case Study Analysis

Authors: Nikita Ravi, Abhinav Goel, James C. Davis, George K. Thiruvathukal

Abstract: The field of deep learning has witnessed significant breakthroughs, spanning various applications, and fundamentally transforming current software capabilities. However, alongside these advancements, there have been increasing concerns about reproducing the results of these deep learning methods. This is significant because reproducibility is the foundation of reliability and validity in software… ▽ More The field of deep learning has witnessed significant breakthroughs, spanning various applications, and fundamentally transforming current software capabilities. However, alongside these advancements, there have been increasing concerns about reproducing the results of these deep learning methods. This is significant because reproducibility is the foundation of reliability and validity in software development, particularly in the rapidly evolving domain of deep learning. The difficulty of reproducibility may arise due to several reasons, including having differences from the original execution environment, incompatible software libraries, proprietary data and source code, lack of transparency, and the stochastic nature in some software. A study conducted by the Nature journal reveals that more than 70% of researchers failed to reproduce other researchers experiments and over 50% failed to reproduce their own experiments. Irreproducibility of deep learning poses significant challenges for researchers and practitioners. To address these concerns, this paper presents a systematic approach at analyzing and improving the reproducibility of deep learning models by demonstrating these guidelines using a case study. We illustrate the patterns and anti-patterns involved with these guidelines for improving the reproducibility of deep learning models. These guidelines encompass establishing a methodology to replicate the original software environment, implementing end-to-end training and testing algorithms, disclosing architectural designs, and enhancing transparency in data processing and training pipelines. We also conduct a sensitivity analysis to understand the model performance across diverse conditions. By implementing these strategies, we aim to bridge the gap between research and practice, so that innovations in deep learning can be effectively reproduced and deployed within software. △ Less

Submitted 6 May, 2025; originally announced May 2025.

Towards a Multimodal Document-grounded Conversational AI System for Education

Authors: Karan Taneja, Anjali Singh, Ashok K. Goel

Abstract: Multimedia learning using text and images has been shown to improve learning outcomes compared to text-only instruction. But conversational AI systems in education predominantly rely on text-based interactions while multimodal conversations for multimedia learning remain unexplored. Moreover, deploying conversational AI in learning contexts requires grounding in reliable sources and verifiability… ▽ More Multimedia learning using text and images has been shown to improve learning outcomes compared to text-only instruction. But conversational AI systems in education predominantly rely on text-based interactions while multimodal conversations for multimedia learning remain unexplored. Moreover, deploying conversational AI in learning contexts requires grounding in reliable sources and verifiability to create trust. We present MuDoC, a Multimodal Document-grounded Conversational AI system based on GPT-4o, that leverages both text and visuals from documents to generate responses interleaved with text and images. Its interface allows verification of AI generated content through seamless navigation to the source. We compare MuDoC to a text-only system to explore differences in learner engagement, trust in AI system, and their performance on problem-solving tasks. Our findings indicate that both visuals and verifiability of content enhance learner engagement and foster trust; however, no significant impact in performance was observed. We draw upon theories from cognitive and learning sciences to interpret the findings and derive implications, and outline future directions for the development of multimodal conversational AI systems in education. △ Less

Submitted 3 April, 2025; originally announced April 2025.

Comments: 15 pages, 4 figures, AIED 2025

Enhanced Question-Answering for Skill-based learning using Knowledge-based AI and Generative AI

Authors: Rahul K. Dass, Rochan H. Madhusudhana, Erin C. Deye, Shashank Verma, Timothy A. Bydlon, Grace Brazil, Ashok K. Goel

Abstract: Supporting learners' understanding of taught skills in online settings is a longstanding challenge. While exercises and chat-based agents can evaluate understanding in limited contexts, this challenge is magnified when learners seek explanations that delve into procedural knowledge (how things are done) and reasoning (why things happen). We hypothesize that an intelligent agent's ability to unders… ▽ More Supporting learners' understanding of taught skills in online settings is a longstanding challenge. While exercises and chat-based agents can evaluate understanding in limited contexts, this challenge is magnified when learners seek explanations that delve into procedural knowledge (how things are done) and reasoning (why things happen). We hypothesize that an intelligent agent's ability to understand and explain learners' questions about skills can be significantly enhanced using the TMK (Task-Method-Knowledge) model, a Knowledge-based AI framework. We introduce Ivy, an intelligent agent that leverages an LLM and iterative refinement techniques to generate explanations that embody teleological, causal, and compositional principles. Our initial evaluation demonstrates that this approach goes beyond the typical shallow responses produced by an agent with access to unstructured text, thereby substantially improving the depth and relevance of feedback. This can potentially ensure learners develop a comprehensive understanding of skills crucial for effective problem-solving in online environments. △ Less

Submitted 10 April, 2025; originally announced April 2025.

Multi-Selection for Recommendation Systems

Authors: Sahasrajit Sarmasarkar, Zhihao Jiang, Ashish Goel, Aleksandra Korolova, Kamesh Munagala

Abstract: We present the construction of a multi-selection model to answer differentially private queries in the context of recommendation systems. The server sends back multiple recommendations and a ``local model'' to the user, which the user can run locally on its device to select the item that best fits its private features. We study a setup where the server uses a deep neural network (trained on the Mo… ▽ More We present the construction of a multi-selection model to answer differentially private queries in the context of recommendation systems. The server sends back multiple recommendations and a ``local model'' to the user, which the user can run locally on its device to select the item that best fits its private features. We study a setup where the server uses a deep neural network (trained on the Movielens 25M dataset as the ground truth for movie recommendation. In the multi-selection paradigm, the average recommendation utility is approximately 97\% of the optimal utility (as determined by the ground truth neural network) while maintaining a local differential privacy guarantee with $ε$ ranging around 1 with respect to feature vectors of neighboring users. This is in comparison to an average recommendation utility of 91\% in the non-multi-selection regime under the same constraints. △ Less

Submitted 9 April, 2025; originally announced April 2025.

Data-driven Fuzzy Control for Time-Optimal Aggressive Trajectory Following

Authors: August Phelps, Juan Augusto Paredes Salazar, Ankit Goel

Abstract: Optimal trajectories that minimize a user-defined cost function in dynamic systems require the solution of a two-point boundary value problem. The optimization process yields an optimal control sequence that depends on the initial conditions and system parameters. However, the optimal sequence may result in undesirable behavior if the system's initial conditions and parameters are erroneous. This… ▽ More Optimal trajectories that minimize a user-defined cost function in dynamic systems require the solution of a two-point boundary value problem. The optimization process yields an optimal control sequence that depends on the initial conditions and system parameters. However, the optimal sequence may result in undesirable behavior if the system's initial conditions and parameters are erroneous. This work presents a data-driven fuzzy controller synthesis framework that is guided by a time-optimal trajectory for multicopter tracking problems. In particular, we consider an aggressive maneuver consisting of a mid-air flip and generate a time-optimal trajectory by numerically solving the two-point boundary value problem. A fuzzy controller consisting of a stabilizing controller near hover conditions and an autoregressive moving average (ARMA) controller, trained to mimic the time-optimal aggressive trajectory, is constructed using the Takagi-Sugeno fuzzy framework. △ Less

Submitted 8 April, 2025; originally announced April 2025.

Comments: 6 pages, 10 figures, submitted to MECC 2025

TurboFuzzLLM: Turbocharging Mutation-based Fuzzing for Effectively Jailbreaking Large Language Models in Practice

Authors: Aman Goel, Xian Carrie Wu, Zhe Wang, Dmitriy Bespalov, Yanjun Qi

Abstract: Jailbreaking large-language models (LLMs) involves testing their robustness against adversarial prompts and evaluating their ability to withstand prompt attacks that could elicit unauthorized or malicious responses. In this paper, we present TurboFuzzLLM, a mutation-based fuzzing technique for efficiently finding a collection of effective jailbreaking templates that, when combined with harmful que… ▽ More Jailbreaking large-language models (LLMs) involves testing their robustness against adversarial prompts and evaluating their ability to withstand prompt attacks that could elicit unauthorized or malicious responses. In this paper, we present TurboFuzzLLM, a mutation-based fuzzing technique for efficiently finding a collection of effective jailbreaking templates that, when combined with harmful questions, can lead a target LLM to produce harmful responses through black-box access via user prompts. We describe the limitations of directly applying existing template-based attacking techniques in practice, and present functional and efficiency-focused upgrades we added to mutation-based fuzzing to generate effective jailbreaking templates automatically. TurboFuzzLLM achieves $\geq$ 95\% attack success rates (ASR) on public datasets for leading LLMs (including GPT-4o \& GPT-4 Turbo), shows impressive generalizability to unseen harmful questions, and helps in improving model defenses to prompt attacks. TurboFuzzLLM is available open source at https://github.com/amazon-science/TurboFuzzLLM. △ Less

Submitted 4 June, 2025; v1 submitted 21 February, 2025; originally announced February 2025.

Comments: Oral presentation at NAACL 2025 industry track

MuDoC: An Interactive Multimodal Document-grounded Conversational AI System

Authors: Karan Taneja, Ashok K. Goel

Abstract: Multimodal AI is an important step towards building effective tools to leverage multiple modalities in human-AI communication. Building a multimodal document-grounded AI system to interact with long documents remains a challenge. Our work aims to fill the research gap of directly leveraging grounded visuals from documents alongside textual content in documents for response generation. We present a… ▽ More Multimodal AI is an important step towards building effective tools to leverage multiple modalities in human-AI communication. Building a multimodal document-grounded AI system to interact with long documents remains a challenge. Our work aims to fill the research gap of directly leveraging grounded visuals from documents alongside textual content in documents for response generation. We present an interactive conversational AI agent 'MuDoC' based on GPT-4o to generate document-grounded responses with interleaved text and figures. MuDoC's intelligent textbook interface promotes trustworthiness and enables verification of system responses by allowing instant navigation to source text and figures in the documents. We also discuss qualitative observations based on MuDoC responses highlighting its strengths and limitations. △ Less

Submitted 13 February, 2025; originally announced February 2025.

Comments: 5 pages, 3 figures, AAAI-MAKE 2025

Metric Distortion of Small-group Deliberation

Authors: Ashish Goel, Mohak Goyal, Kamesh Munagala

Abstract: We consider models for social choice where voters rank a set of choices (or alternatives) by deliberating in small groups of size at most $k$, and these outcomes are aggregated by a social choice rule to find the winning alternative. We ground these models in the metric distortion framework, where the voters and alternatives are embedded in a latent metric space, with closer alternative being more… ▽ More We consider models for social choice where voters rank a set of choices (or alternatives) by deliberating in small groups of size at most $k$, and these outcomes are aggregated by a social choice rule to find the winning alternative. We ground these models in the metric distortion framework, where the voters and alternatives are embedded in a latent metric space, with closer alternative being more desirable for a voter. We posit that the outcome of a small-group interaction optimally uses the voters' collective knowledge of the metric, either deterministically or probabilistically. We characterize the distortion of our deliberation models for small $k$, showing that groups of size $k=3$ suffice to drive the distortion bound below the deterministic metric distortion lower bound of $3$, and groups of size $4$ suffice to break the randomized lower bound of $2.11$. We also show nearly tight asymptotic distortion bounds in the group size, showing that for any constant $ε> 0$, achieving a distortion of $1+ε$ needs group size that only depends on $1/ε$, and not the number of alternatives. We obtain these results via formulating a basic optimization problem in small deviations of the sum of $i.i.d.$ random variables, which we solve to global optimality via non-convex optimization. The resulting bounds may be of independent interest in probability theory. △ Less

Submitted 20 March, 2025; v1 submitted 3 February, 2025; originally announced February 2025.

Comments: To appear in ACM STOC 2025

Differentially Private Steering for Large Language Model Alignment

Authors: Anmol Goel, Yaxi Hu, Iryna Gurevych, Amartya Sanyal

Abstract: Aligning Large Language Models (LLMs) with human values and away from undesirable behaviors (such as hallucination) has become increasingly important. Recently, steering LLMs towards a desired behavior via activation editing has emerged as an effective method to mitigate harmful generations at inference-time. Activation editing modifies LLM representations by preserving information from positive d… ▽ More Aligning Large Language Models (LLMs) with human values and away from undesirable behaviors (such as hallucination) has become increasingly important. Recently, steering LLMs towards a desired behavior via activation editing has emerged as an effective method to mitigate harmful generations at inference-time. Activation editing modifies LLM representations by preserving information from positive demonstrations (e.g., truthful) and minimising information from negative demonstrations (e.g., hallucinations). When these demonstrations come from a private dataset, the aligned LLM may leak private information contained in those private samples. In this work, we present the first study of aligning LLM behavior with private datasets. Our work proposes the Private Steering for LLM Alignment (PSA) algorithm to edit LLM activations with differential privacy (DP) guarantees. We conduct extensive experiments on seven different benchmarks with open-source LLMs of different sizes (0.5B to 7B) and model families (LlaMa, Qwen, Mistral and Gemma). Our results show that PSA achieves DP guarantees for LLM alignment with minimal loss in performance, including alignment metrics, open-ended text generation quality, and general-purpose reasoning. We also develop the first Membership Inference Attack (MIA) for evaluating and auditing the empirical privacy for the problem of LLM steering via activation editing. Our experiments support the theoretical guarantees by showing improved guarantees for our PSA algorithm compared to several existing non-private techniques. △ Less

Submitted 20 March, 2025; v1 submitted 30 January, 2025; originally announced January 2025.

Comments: ICLR 2025 Camera Ready; Code: https://github.com/UKPLab/iclr2025-psa

TractoGPT: A GPT architecture for White Matter Segmentation

Authors: Anoushkrit Goel, Simroop Singh, Ankita Joshi, Ranjeet Ranjan Jha, Chirag Ahuja, Aditya Nigam, Arnav Bhavsar

Abstract: White matter bundle segmentation is crucial for studying brain structural connectivity, neurosurgical planning, and neurological disorders. White Matter Segmentation remains challenging due to structural similarity in streamlines, subject variability, symmetry in 2 hemispheres, etc. To address these challenges, we propose TractoGPT, a GPT-based architecture trained on streamline, cluster, and fusi… ▽ More White matter bundle segmentation is crucial for studying brain structural connectivity, neurosurgical planning, and neurological disorders. White Matter Segmentation remains challenging due to structural similarity in streamlines, subject variability, symmetry in 2 hemispheres, etc. To address these challenges, we propose TractoGPT, a GPT-based architecture trained on streamline, cluster, and fusion data representations separately. TractoGPT is a fully-automatic method that generalizes across datasets and retains shape information of the white matter bundles. Experiments also show that TractoGPT outperforms state-of-the-art methods on average DICE, Overlap and Overreach scores. We use TractoInferno and 105HCP datasets and validate generalization across dataset. △ Less

Submitted 21 February, 2025; v1 submitted 26 January, 2025; originally announced January 2025.

Comments: Accepted as a conference paper at 23rd IEEE International Symposium on Biomedical Imaging 2025. IEEE holds the copyright for this publication

Self-Explanation in Social AI Agents

Authors: Rhea Basappa, Mustafa Tekman, Hong Lu, Benjamin Faught, Sandeep Kakar, Ashok K. Goel

Abstract: Social AI agents interact with members of a community, thereby changing the behavior of the community. For example, in online learning, an AI social assistant may connect learners and thereby enhance social interaction. These social AI assistants too need to explain themselves in order to enhance transparency and trust with the learners. We present a method of self-explanation that uses introspect… ▽ More Social AI agents interact with members of a community, thereby changing the behavior of the community. For example, in online learning, an AI social assistant may connect learners and thereby enhance social interaction. These social AI assistants too need to explain themselves in order to enhance transparency and trust with the learners. We present a method of self-explanation that uses introspection over a self-model of an AI social assistant. The self-model is captured as a functional model that specifies how the methods of the agent use knowledge to achieve its tasks. The process of generating self-explanations uses Chain of Thought to reflect on the self-model and ChatGPT to provide explanations about its functioning. We evaluate the self-explanation of the AI social assistant for completeness and correctness. We also report on its deployment in a live class. △ Less

Submitted 18 January, 2025; originally announced January 2025.

Comments: Extended version of the paper published in International Conference on Intelligent Tutoring Systems, pages 351-360, 2024, Springer. Images corrected, and live deployment, ablation, and precision study results added

The Textbook of Tomorrow: Rethinking Course Material Interfacing in the Era of GPT

Authors: Audrey Olson, Pratyusha Maiti, Ashok Goel

Abstract: Online Learning Management Systems (LMSs), such as Blackboard and Canvas, have existed for decades. Yet, course readings, when provided at all, consistently exist as simple digital twins to their real-life counterparts. While online tools and resources exist to help students process digital texts more efficiently or in ways better suited to their learning styles, knowledge about such resources is… ▽ More Online Learning Management Systems (LMSs), such as Blackboard and Canvas, have existed for decades. Yet, course readings, when provided at all, consistently exist as simple digital twins to their real-life counterparts. While online tools and resources exist to help students process digital texts more efficiently or in ways better suited to their learning styles, knowledge about such resources is not evenly distributed and creates a gulf in advantage between students. This paper proposes the courseware integration of "smart" textbooks, a newfound way for students to chat with their readings, receive summaries and explanations for highlighted text, and generate quiz questions via an AI agent embedded in their online course material. Future iterations of the software aim to add in-context reference highlighting for AI-generated answers and personalized tunings for the end learner. △ Less

Submitted 7 January, 2025; originally announced January 2025.

Comments: 5 pages, 2 figures

Attributing Culture-Conditioned Generations to Pretraining Corpora

Authors: Huihan Li, Arnav Goel, Keyu He, Xiang Ren

Abstract: In open-ended generative tasks like narrative writing or dialogue, large language models often exhibit cultural biases, showing limited knowledge and generating templated outputs for less prevalent cultures. Recent works show that these biases may stem from uneven cultural representation in pretraining corpora. This work investigates how pretraining leads to biased culture-conditioned generations… ▽ More In open-ended generative tasks like narrative writing or dialogue, large language models often exhibit cultural biases, showing limited knowledge and generating templated outputs for less prevalent cultures. Recent works show that these biases may stem from uneven cultural representation in pretraining corpora. This work investigates how pretraining leads to biased culture-conditioned generations by analyzing how models associate entities with cultures based on pretraining data patterns. We propose the MEMOed framework (MEMOrization from pretraining document) to determine whether a generation for a culture arises from memorization. Using MEMOed on culture-conditioned generations about food and clothing for 110 cultures, we find that high-frequency cultures in pretraining data yield more generations with memorized symbols, while some low-frequency cultures produce none. Additionally, the model favors generating entities with extraordinarily high frequency regardless of the conditioned culture, reflecting biases toward frequent pretraining terms irrespective of relevance. We hope that the MEMOed framework and our insights will inspire more works on attributing model performance on pretraining data. △ Less

Submitted 19 March, 2025; v1 submitted 30 December, 2024; originally announced December 2024.

ETTA: Elucidating the Design Space of Text-to-Audio Models

Authors: Sang-gil Lee, Zhifeng Kong, Arushi Goel, Sungwon Kim, Rafael Valle, Bryan Catanzaro

Abstract: Recent years have seen significant progress in Text-To-Audio (TTA) synthesis, enabling users to enrich their creative workflows with synthetic audio generated from natural language prompts. Despite this progress, the effects of data, model architecture, training objective functions, and sampling strategies on target benchmarks are not well understood. With the purpose of providing a holistic under… ▽ More Recent years have seen significant progress in Text-To-Audio (TTA) synthesis, enabling users to enrich their creative workflows with synthetic audio generated from natural language prompts. Despite this progress, the effects of data, model architecture, training objective functions, and sampling strategies on target benchmarks are not well understood. With the purpose of providing a holistic understanding of the design space of TTA models, we set up a large-scale empirical experiment focused on diffusion and flow matching models. Our contributions include: 1) AF-Synthetic, a large dataset of high quality synthetic captions obtained from an audio understanding model; 2) a systematic comparison of different architectural, training, and inference design choices for TTA models; 3) an analysis of sampling methods and their Pareto curves with respect to generation quality and inference speed. We leverage the knowledge obtained from this extensive analysis to propose our best model dubbed Elucidated Text-To-Audio (ETTA). When evaluated on AudioCaps and MusicCaps, ETTA provides improvements over the baselines trained on publicly available data, while being competitive with models trained on proprietary data. Finally, we show ETTA's improved ability to generate creative audio following complex and imaginative captions -- a task that is more challenging than current benchmarks. △ Less

Submitted 30 June, 2025; v1 submitted 26 December, 2024; originally announced December 2024.

Comments: ICML 2025. Demo: https://research.nvidia.com/labs/adlr/ETTA/ Code: https://github.com/NVIDIA/elucidated-text-to-audio

Health AI Developer Foundations

Authors: Atilla P. Kiraly, Sebastien Baur, Kenneth Philbrick, Fereshteh Mahvar, Liron Yatziv, Tiffany Chen, Bram Sterling, Nick George, Fayaz Jamil, Jing Tang, Kai Bailey, Faruk Ahmed, Akshay Goel, Abbi Ward, Lin Yang, Andrew Sellergren, Yossi Matias, Avinatan Hassidim, Shravya Shetty, Daniel Golden, Shekoofeh Azizi, David F. Steiner, Yun Liu, Tim Thelin, Rory Pilgrim , et al. (1 additional authors not shown)

Abstract: Robust medical Machine Learning (ML) models have the potential to revolutionize healthcare by accelerating clinical research, improving workflows and outcomes, and producing novel insights or capabilities. Developing such ML models from scratch is cost prohibitive and requires substantial compute, data, and time (e.g., expert labeling). To address these challenges, we introduce Health AI Developer… ▽ More Robust medical Machine Learning (ML) models have the potential to revolutionize healthcare by accelerating clinical research, improving workflows and outcomes, and producing novel insights or capabilities. Developing such ML models from scratch is cost prohibitive and requires substantial compute, data, and time (e.g., expert labeling). To address these challenges, we introduce Health AI Developer Foundations (HAI-DEF), a suite of pre-trained, domain-specific foundation models, tools, and recipes to accelerate building ML for health applications. The models cover various modalities and domains, including radiology (X-rays and computed tomography), histopathology, dermatological imaging, and audio. These models provide domain specific embeddings that facilitate AI development with less labeled data, shorter training times, and reduced computational costs compared to traditional approaches. In addition, we utilize a common interface and style across these models, and prioritize usability to enable developers to integrate HAI-DEF efficiently. We present model evaluations across various tasks and conclude with a discussion of their application and evaluation, covering the importance of ensuring efficacy, fairness, and equity. Finally, while HAI-DEF and specifically the foundation models lower the barrier to entry for ML in healthcare, we emphasize the importance of validation with problem- and population-specific data for each desired usage setting. This technical report will be updated over time as more modalities and features are added. △ Less

Submitted 26 November, 2024; v1 submitted 22 November, 2024; originally announced November 2024.

Comments: 16 pages, 8 figures

TractoEmbed: Modular Multi-level Embedding framework for white matter tract segmentation

Authors: Anoushkrit Goel, Bipanjit Singh, Ankita Joshi, Ranjeet Ranjan Jha, Chirag Ahuja, Aditya Nigam, Arnav Bhavsar

Abstract: White matter tract segmentation is crucial for studying brain structural connectivity and neurosurgical planning. However, segmentation remains challenging due to issues like class imbalance between major and minor tracts, structural similarity, subject variability, symmetric streamlines between hemispheres etc. To address these challenges, we propose TractoEmbed, a modular multi-level embedding f… ▽ More White matter tract segmentation is crucial for studying brain structural connectivity and neurosurgical planning. However, segmentation remains challenging due to issues like class imbalance between major and minor tracts, structural similarity, subject variability, symmetric streamlines between hemispheres etc. To address these challenges, we propose TractoEmbed, a modular multi-level embedding framework, that encodes localized representations through learning tasks in respective encoders. In this paper, TractoEmbed introduces a novel hierarchical streamline data representation that captures maximum spatial information at each level i.e. individual streamlines, clusters, and patches. Experiments show that TractoEmbed outperforms state-of-the-art methods in white matter tract segmentation across different datasets, and spanning various age groups. The modular framework directly allows the integration of additional embeddings in future works. △ Less

Submitted 12 November, 2024; originally announced November 2024.

Comments: Accepted at 27th International Conference on Pattern Recognition (ICPR), 2024 15 pages, 2 figures

Flight Demonstration and Model Validation of a Prototype Variable-Altitude Venus Aerobot

Authors: Jacob S. Izraelevitz, Siddharth Krishnamoorthy, Ashish Goel, Caleb Turner, Carolina Aiazzi, Michael Pauken, Kevin Carlson, Gerald Walsh, Carl Leake, Carlos Quintana, Christopher Lim, Abhi Jain, Leonard Dorsky, Kevin Baines, James Cutts, Paul K. Byrne, Tim Lachenmeier, Jeffery L. Hall

Abstract: This paper details a significant milestone towards maturing a buoyant aerial robotic platform, or aerobot, for flight in the Venus clouds. We describe two flights of our subscale altitude-controlled aerobot, fabricated from the materials necessary to survive Venus conditions. During these flights over the Nevada Black Rock desert, the prototype flew at the identical atmospheric densities as 54 to… ▽ More This paper details a significant milestone towards maturing a buoyant aerial robotic platform, or aerobot, for flight in the Venus clouds. We describe two flights of our subscale altitude-controlled aerobot, fabricated from the materials necessary to survive Venus conditions. During these flights over the Nevada Black Rock desert, the prototype flew at the identical atmospheric densities as 54 to 55 km cloud layer altitudes on Venus. We further describe a first-principle aerobot dynamics model which we validate against the Nevada flight data and subsequently employ to predict the performance of future aerobots on Venus. The aerobot discussed in this paper is under JPL development for an in-situ mission flying multiple circumnavigations of Venus, sampling the chemical and physical properties of the planet's atmosphere and also remotely sensing surface properties. △ Less

Submitted 10 November, 2024; originally announced November 2024.

Comments: Preprint submitted to AIAA Journal of Aircraft

Tract-RLFormer: A Tract-Specific RL policy based Decoder-only Transformer Network

Authors: Ankita Joshi, Ashutosh Sharma, Anoushkrit Goel, Ranjeet Ranjan Jha, Chirag Ahuja, Arnav Bhavsar, Aditya Nigam

Abstract: Fiber tractography is a cornerstone of neuroimaging, enabling the detailed mapping of the brain's white matter pathways through diffusion MRI. This is crucial for understanding brain connectivity and function, making it a valuable tool in neurological applications. Despite its importance, tractography faces challenges due to its complexity and susceptibility to false positives, misrepresenting vit… ▽ More Fiber tractography is a cornerstone of neuroimaging, enabling the detailed mapping of the brain's white matter pathways through diffusion MRI. This is crucial for understanding brain connectivity and function, making it a valuable tool in neurological applications. Despite its importance, tractography faces challenges due to its complexity and susceptibility to false positives, misrepresenting vital pathways. To address these issues, recent strategies have shifted towards deep learning, utilizing supervised learning, which depends on precise ground truth, or reinforcement learning, which operates without it. In this work, we propose Tract-RLFormer, a network utilizing both supervised and reinforcement learning, in a two-stage policy refinement process that markedly improves the accuracy and generalizability across various data-sets. By employing a tract-specific approach, our network directly delineates the tracts of interest, bypassing the traditional segmentation process. Through rigorous validation on datasets such as TractoInferno, HCP, and ISMRM-2015, our methodology demonstrates a leap forward in tractography, showcasing its ability to accurately map the brain's white matter tracts. △ Less

Submitted 14 November, 2024; v1 submitted 8 November, 2024; originally announced November 2024.

Comments: Accepted at 27th International Conference on Pattern Recognition (ICPR), 2024

Interchangeable Token Embeddings for Extendable Vocabulary and Alpha-Equivalence

Authors: İlker Işık, Ramazan Gokberk Cinbis, Ebru Aydin Gol

Abstract: Language models lack the notion of interchangeable tokens: symbols that are semantically equivalent yet distinct, such as bound variables in formal logic. This limitation prevents generalization to larger vocabularies and hinders the model's ability to recognize alpha-equivalence, where renaming bound variables preserves meaning. We formalize this machine learning problem and introduce alpha-covar… ▽ More Language models lack the notion of interchangeable tokens: symbols that are semantically equivalent yet distinct, such as bound variables in formal logic. This limitation prevents generalization to larger vocabularies and hinders the model's ability to recognize alpha-equivalence, where renaming bound variables preserves meaning. We formalize this machine learning problem and introduce alpha-covariance, a metric for evaluating robustness to such transformations. To tackle this task, we propose a dual-part token embedding strategy: a shared component ensures semantic consistency, while a randomized component maintains token distinguishability. Compared to a baseline that relies on alpha-renaming for data augmentation, our approach demonstrates improved generalization to unseen tokens in linear temporal logic solving, propositional logic assignment prediction, and copying with an extendable vocabulary, while introducing a favorable inductive bias for alpha-equivalence. Our findings establish a foundation for designing language models that can learn interchangeable token representations, a crucial step toward more flexible and systematic reasoning in formal domains. Our code and project page are available at https://necrashter.github.io/interchangeable-token-embeddings △ Less

Submitted 18 June, 2025; v1 submitted 22 October, 2024; originally announced October 2024.

Comments: ICML 2025 Poster Paper, Camera Ready Version

OMCAT: Omni Context Aware Transformer

Authors: Arushi Goel, Karan Sapra, Matthieu Le, Rafael Valle, Andrew Tao, Bryan Catanzaro

Abstract: Large Language Models (LLMs) have made significant strides in text generation and comprehension, with recent advancements extending into multimodal LLMs that integrate visual and audio inputs. However, these models continue to struggle with fine-grained, cross-modal temporal understanding, particularly when correlating events across audio and video streams. We address these challenges with two key… ▽ More Large Language Models (LLMs) have made significant strides in text generation and comprehension, with recent advancements extending into multimodal LLMs that integrate visual and audio inputs. However, these models continue to struggle with fine-grained, cross-modal temporal understanding, particularly when correlating events across audio and video streams. We address these challenges with two key contributions: a new dataset and model, called OCTAV and OMCAT respectively. OCTAV (Omni Context and Temporal Audio Video) is a novel dataset designed to capture event transitions across audio and video. Second, OMCAT (Omni Context Aware Transformer) is a powerful model that leverages RoTE (Rotary Time Embeddings), an innovative extension of RoPE, to enhance temporal grounding and computational efficiency in time-anchored tasks. Through a robust three-stage training pipeline-feature alignment, instruction tuning, and OCTAV-specific training-OMCAT excels in cross-modal temporal understanding. Our model demonstrates state-of-the-art performance on Audio-Visual Question Answering (AVQA) tasks and the OCTAV benchmark, showcasing significant gains in temporal reasoning and cross-modal alignment, as validated through comprehensive experiments and ablation studies. Our dataset and code will be made publicly available. The link to our demo page is https://om-cat.github.io. △ Less

Submitted 15 October, 2024; originally announced October 2024.

Comments: Demo page: https://om-cat.github.io

Time-Series Foundation AI Model for Value-at-Risk Forecasting

Authors: Anubha Goel, Puneet Pasricha, Juho Kanniainen

Abstract: This study is the first to analyze the performance of a time-series foundation AI model for Value-at-Risk (VaR), which essentially forecasts the left-tail quantiles of returns. Foundation models, pre-trained on diverse datasets, can be applied in a zero-shot setting with minimal data or further improved through finetuning. We compare Google's TimesFM model to conventional parametric and non-parame… ▽ More This study is the first to analyze the performance of a time-series foundation AI model for Value-at-Risk (VaR), which essentially forecasts the left-tail quantiles of returns. Foundation models, pre-trained on diverse datasets, can be applied in a zero-shot setting with minimal data or further improved through finetuning. We compare Google's TimesFM model to conventional parametric and non-parametric models, including GARCH and Generalized Autoregressive Score (GAS), using 19 years of daily returns from the SP 100 index and its constituents. Backtesting with over 8.5 years of out-of-sample data shows that the fine-tuned foundation model consistently outperforms traditional methods in actual-over-expected ratios. For the quantile score loss function, it performs comparably to the best econometric model, GAS. Overall, the foundation model ranks as the best or among the top performers across the 0.01, 0.025, 0.05, and 0.1 quantile forecasting. Fine-tuning significantly improves accuracy, showing that zero-shot use is not optimal for VaR. △ Less

Submitted 12 May, 2025; v1 submitted 15 October, 2024; originally announced October 2024.

A Novel Neural Filter to Improve Accuracy of Neural Network Models of Dynamic Systems

Authors: Parham Oveissi, Turibius Rozario, Ankit Goel

Abstract: The application of neural networks in modeling dynamic systems has become prominent due to their ability to estimate complex nonlinear functions. Despite their effectiveness, neural networks face challenges in long-term predictions, where the prediction error diverges over time, thus degrading their accuracy. This paper presents a neural filter to enhance the accuracy of long-term state prediction… ▽ More The application of neural networks in modeling dynamic systems has become prominent due to their ability to estimate complex nonlinear functions. Despite their effectiveness, neural networks face challenges in long-term predictions, where the prediction error diverges over time, thus degrading their accuracy. This paper presents a neural filter to enhance the accuracy of long-term state predictions of neural network-based models of dynamic systems. Motivated by the extended Kalman filter, the neural filter combines the neural network state predictions with the measurements from the physical system to improve the estimated state's accuracy. The neural filter's improvements in prediction accuracy are demonstrated through applications to four nonlinear dynamical systems. Numerical experiments show that the neural filter significantly improves prediction accuracy and bounds the state estimate covariance, outperforming the neural network predictions. Furthermore, it is also shown that the accuracy of a poorly trained neural network model can be improved to the same level as that of an adequately trained neural network model, potentially decreasing the training cost and required data to train a neural network. △ Less

Submitted 7 June, 2025; v1 submitted 20 September, 2024; originally announced September 2024.

Estimating Contribution Quality in Online Deliberations Using a Large Language Model

Authors: Lodewijk Gelauff, Mohak Goyal, Bhargav Dindukurthi, Ashish Goel, Alice Siu

Abstract: Deliberation involves participants exchanging knowledge, arguments, and perspectives and has been shown to be effective at addressing polarization. The Stanford Online Deliberation Platform facilitates large-scale deliberations. It enables video-based online discussions on a structured agenda for small groups without requiring human moderators. This paper's data comes from various deliberation eve… ▽ More Deliberation involves participants exchanging knowledge, arguments, and perspectives and has been shown to be effective at addressing polarization. The Stanford Online Deliberation Platform facilitates large-scale deliberations. It enables video-based online discussions on a structured agenda for small groups without requiring human moderators. This paper's data comes from various deliberation events, including one conducted in collaboration with Meta in 32 countries, and another with 38 post-secondary institutions in the US. Estimating the quality of contributions in a conversation is crucial for assessing feature and intervention impacts. Traditionally, this is done by human annotators, which is time-consuming and costly. We use a large language model (LLM) alongside eight human annotators to rate contributions based on justification, novelty, expansion of the conversation, and potential for further expansion, with scores ranging from 1 to 5. Annotators also provide brief justifications for their ratings. Using the average rating from other human annotators as the ground truth, we find the model outperforms individual human annotators. While pairs of human annotators outperform the model in rating justification and groups of three outperform it on all four metrics, the model remains competitive. We illustrate the usefulness of the automated quality rating by assessing the effect of nudges on the quality of deliberation. We first observe that individual nudges after prolonged inactivity are highly effective, increasing the likelihood of the individual requesting to speak in the next 30 seconds by 65%. Using our automated quality estimation, we show that the quality ratings for statements prompted by nudging are similar to those made without nudging, signifying that nudging leads to more ideas being generated in the conversation without losing overall quality. △ Less

Submitted 21 August, 2024; originally announced August 2024.

ACM Class: I.2.1; J.5; H.5.3

Few-shot Scooping Under Domain Shift via Simulated Maximal Deployment Gaps

Authors: Yifan Zhu, Pranay Thangeda, Erica L Tevere, Ashish Goel, Erik Kramer, Hari D Nayar, Melkior Ornik, Kris Hauser

Abstract: Autonomous lander missions on extraterrestrial bodies need to sample granular materials while coping with domain shifts, even when sampling strategies are extensively tuned on Earth. To tackle this challenge, this paper studies the few-shot scooping problem and proposes a vision-based adaptive scooping strategy that uses the deep kernel Gaussian process method trained with a novel meta-training st… ▽ More Autonomous lander missions on extraterrestrial bodies need to sample granular materials while coping with domain shifts, even when sampling strategies are extensively tuned on Earth. To tackle this challenge, this paper studies the few-shot scooping problem and proposes a vision-based adaptive scooping strategy that uses the deep kernel Gaussian process method trained with a novel meta-training strategy to learn online from very limited experience on out-of-distribution target terrains. Our Deep Kernel Calibration with Maximal Deployment Gaps (kCMD) strategy explicitly trains a deep kernel model to adapt to large domain shifts by creating simulated maximal deployment gaps from an offline training dataset and training models to overcome these deployment gaps during training. Employed in a Bayesian Optimization sequential decision-making framework, the proposed method allows the robot to perform high-quality scooping actions on out-of-distribution terrains after a few attempts, significantly outperforming non-adaptive methods proposed in the excavation literature as well as other state-of-the-art meta-learning methods. The proposed method also demonstrates zero-shot transfer capability, successfully adapting to the NASA OWLAT platform, which serves as a state-of-the-art simulator for potential future planetary missions. These results demonstrate the potential of training deep models with simulated deployment gaps for more generalizable meta-learning in high-capacity models. Furthermore, they highlight the promise of our method in autonomous lander sampling missions by enabling landers to overcome the deployment gap between Earth and extraterrestrial bodies. △ Less

Submitted 6 August, 2024; originally announced August 2024.

Comments: arXiv admin note: substantial text overlap with arXiv:2303.02893

Integrating Cognitive AI with Generative Models for Enhanced Question Answering in Skill-based Learning

Authors: Rochan H. Madhusudhana, Rahul K. Dass, Jeanette Luu, Ashok K. Goel

Abstract: In online learning, the ability to provide quick and accurate feedback to learners is crucial. In skill-based learning, learners need to understand the underlying concepts and mechanisms of a skill to be able to apply it effectively. While videos are a common tool in online learning, they cannot comprehend or assess the skills being taught. Additionally, while Generative AI methods are effective i… ▽ More In online learning, the ability to provide quick and accurate feedback to learners is crucial. In skill-based learning, learners need to understand the underlying concepts and mechanisms of a skill to be able to apply it effectively. While videos are a common tool in online learning, they cannot comprehend or assess the skills being taught. Additionally, while Generative AI methods are effective in searching and retrieving answers from a text corpus, it remains unclear whether these methods exhibit any true understanding. This limits their ability to provide explanations of skills or help with problem-solving. This paper proposes a novel approach that merges Cognitive AI and Generative AI to address these challenges. We employ a structured knowledge representation, the TMK (Task-Method-Knowledge) model, to encode skills taught in an online Knowledge-based AI course. Leveraging techniques such as Large Language Models, Chain-of-Thought, and Iterative Refinement, we outline a framework for generating reasoned explanations in response to learners' questions about skills. △ Less

Submitted 2 August, 2024; v1 submitted 28 July, 2024; originally announced July 2024.

Comments: 9 pages, 6 figures, 1 table

Combining Cognitive and Generative AI for Self-explanation in Interactive AI Agents

Authors: Shalini Sushri, Rahul Dass, Rhea Basappa, Hong Lu, Ashok Goel

Abstract: The Virtual Experimental Research Assistant (VERA) is an inquiry-based learning environment that empowers a learner to build conceptual models of complex ecological systems and experiment with agent-based simulations of the models. This study investigates the convergence of cognitive AI and generative AI for self-explanation in interactive AI agents such as VERA. From a cognitive AI viewpoint, we… ▽ More The Virtual Experimental Research Assistant (VERA) is an inquiry-based learning environment that empowers a learner to build conceptual models of complex ecological systems and experiment with agent-based simulations of the models. This study investigates the convergence of cognitive AI and generative AI for self-explanation in interactive AI agents such as VERA. From a cognitive AI viewpoint, we endow VERA with a functional model of its own design, knowledge, and reasoning represented in the Task--Method--Knowledge (TMK) language. From the perspective of generative AI, we use ChatGPT, LangChain, and Chain-of-Thought to answer user questions based on the VERA TMK model. Thus, we combine cognitive and generative AI to generate explanations about how VERA works and produces its answers. The preliminary evaluation of the generation of explanations in VERA on a bank of 66 questions derived from earlier work appears promising. △ Less

Submitted 25 July, 2024; originally announced July 2024.

Comments: 10 pages, 2 figures, 2 tables, 1 appendix, HEXED Workshop @EDM July 2024

How Do Students Interact with an LLM-powered Virtual Teaching Assistant in Different Educational Settings?

Authors: Pratyusha Maiti, Ashok K. Goel

Abstract: Jill Watson, a virtual teaching assistant powered by LLMs, answers student questions and engages them in extended conversations on courseware provided by the instructors. In this paper, we analyze student interactions with Jill across multiple courses and colleges, focusing on the types and complexity of student questions based on Bloom's Revised Taxonomy and tool usage patterns. We find that, by… ▽ More Jill Watson, a virtual teaching assistant powered by LLMs, answers student questions and engages them in extended conversations on courseware provided by the instructors. In this paper, we analyze student interactions with Jill across multiple courses and colleges, focusing on the types and complexity of student questions based on Bloom's Revised Taxonomy and tool usage patterns. We find that, by supporting a wide range of cognitive demands, Jill encourages students to engage in sophisticated, higher-order cognitive questions. However, the frequency of usage varies significantly across deployments, and the types of questions asked depend on course-specific contexts. These findings pave the way for future work on AI-driven educational tools tailored to individual learning styles and course structure, potentially enhancing both the teaching and learning experience in classrooms. △ Less

Submitted 25 July, 2024; v1 submitted 14 July, 2024; originally announced July 2024.

Comments: Accepted in the Seventeenth International Conference on Educational Data Mining (EDM) Workshop: Leveraging LLMs for Next Generation Educational Technologies, July 2024

Differential Privacy with Multiple Selections

Authors: Ashish Goel, Zhihao Jiang, Aleksandra Korolova, Kamesh Munagala, Sahasrajit Sarmasarkar

Abstract: We consider the setting where a user with sensitive features wishes to obtain a recommendation from a server in a differentially private fashion. We propose a ``multi-selection'' architecture where the server can send back multiple recommendations and the user chooses one from these that matches best with their private features. When the user feature is one-dimensional -- on an infinite line -- an… ▽ More We consider the setting where a user with sensitive features wishes to obtain a recommendation from a server in a differentially private fashion. We propose a ``multi-selection'' architecture where the server can send back multiple recommendations and the user chooses one from these that matches best with their private features. When the user feature is one-dimensional -- on an infinite line -- and the accuracy measure is defined w.r.t some increasing function $\mathfrak{h}(.)$ of the distance on the line, we precisely characterize the optimal mechanism that satisfies differential privacy. The specification of the optimal mechanism includes both the distribution of the noise that the user adds to its private value, and the algorithm used by the server to determine the set of results to send back as a response and further show that Laplace is an optimal noise distribution. We further show that this optimal mechanism results in an error that is inversely proportional to the number of results returned when the function $\mathfrak{h}(.)$ is the identity function. △ Less

Submitted 19 July, 2024; originally announced July 2024.

Distributed Instruments for Planetary Surface Science: Scientific Opportunities and Technology Feasibility

Authors: Federico Rossi, Robert C. Anderson, Saptarshi Bandyopadhyay, Erik Brandon, Ashish Goel, Joshua Vander Hook, Michael Mischna, Michaela Villarreal, Mark Wronkiewicz

Abstract: In this paper, we assess the scientific promise and technology feasibility of distributed instruments for planetary science. A distributed instrument is an instrument designed to collect spatially and temporally correlated data from multiple networked, geographically distributed point sensors. Distributed instruments are ubiquitous in Earth science, where they are routinely employed for weather an… ▽ More In this paper, we assess the scientific promise and technology feasibility of distributed instruments for planetary science. A distributed instrument is an instrument designed to collect spatially and temporally correlated data from multiple networked, geographically distributed point sensors. Distributed instruments are ubiquitous in Earth science, where they are routinely employed for weather and climate science, seismic studies and resource prospecting, and detection of industrial emissions. However, to date, their adoption in planetary surface science has been minimal. It is natural to ask whether this lack of adoption is driven by low potential to address high-priority questions in planetary science; immature technology; or both. To address this question, we survey high-priority planetary science questions that are uniquely well-suited to distributed instruments. We identify four areas of research where distributed instruments hold promise to unlock answers that are largely inaccessible to monolithic sensors, namely, weather and climate studies of Mars; localization of seismic events on rocky and icy bodies; localization of trace gas emissions, primarily on Mars; and magnetometry studies of internal composition. Next, we survey enabling technologies for distributed sensors and assess their maturity. We identify sensor placement (including descent and landing on planetary surfaces), power, and instrument autonomy as three key areas requiring further investment to enable future distributed instruments. Overall, this work shows that distributed instruments hold great promise for planetary science, and paves the way for follow-on studies of future distributed instruments for Solar System in-situ science. △ Less

Submitted 1 July, 2024; originally announced July 2024.

Exploring Multilingual Unseen Speaker Emotion Recognition: Leveraging Co-Attention Cues in Multitask Learning

Authors: Arnav Goel, Medha Hira, Anubha Gupta

Abstract: Advent of modern deep learning techniques has given rise to advancements in the field of Speech Emotion Recognition (SER). However, most systems prevalent in the field fail to generalize to speakers not seen during training. This study focuses on handling challenges of multilingual SER, specifically on unseen speakers. We introduce CAMuLeNet, a novel architecture leveraging co-attention based fusi… ▽ More Advent of modern deep learning techniques has given rise to advancements in the field of Speech Emotion Recognition (SER). However, most systems prevalent in the field fail to generalize to speakers not seen during training. This study focuses on handling challenges of multilingual SER, specifically on unseen speakers. We introduce CAMuLeNet, a novel architecture leveraging co-attention based fusion and multitask learning to address this problem. Additionally, we benchmark pretrained encoders of Whisper, HuBERT, Wav2Vec2.0, and WavLM using 10-fold leave-speaker-out cross-validation on five existing multilingual benchmark datasets: IEMOCAP, RAVDESS, CREMA-D, EmoDB and CaFE and, release a novel dataset for SER on the Hindi language (BhavVani). CAMuLeNet shows an average improvement of approximately 8% over all benchmarks on unseen speakers determined by our cross-validation strategy. △ Less

Submitted 19 June, 2024; v1 submitted 13 June, 2024; originally announced June 2024.

Comments: 5 pages, Accepted to INTERSPEECH 2024. The first two authors contributed equally

Multilingual Prosody Transfer: Comparing Supervised & Transfer Learning

Authors: Arnav Goel, Medha Hira, Anubha Gupta

Abstract: The field of prosody transfer in speech synthesis systems is rapidly advancing. This research is focused on evaluating learning methods for adapting pre-trained monolingual text-to-speech (TTS) models to multilingual conditions, i.e., Supervised Fine-Tuning (SFT) and Transfer Learning (TL). This comparison utilizes three distinct metrics: Mean Opinion Score (MOS), Recognition Accuracy (RA), and Me… ▽ More The field of prosody transfer in speech synthesis systems is rapidly advancing. This research is focused on evaluating learning methods for adapting pre-trained monolingual text-to-speech (TTS) models to multilingual conditions, i.e., Supervised Fine-Tuning (SFT) and Transfer Learning (TL). This comparison utilizes three distinct metrics: Mean Opinion Score (MOS), Recognition Accuracy (RA), and Mel Cepstral Distortion (MCD). Results demonstrate that, in comparison to SFT, TL leads to significantly enhanced performance, with an average MOS higher by 1.53 points, a 37.5% increase in RA, and approximately a 7.8-point improvement in MCD. These findings are instrumental in helping build TTS models for low-resource languages. △ Less

Submitted 18 June, 2024; v1 submitted 23 May, 2024; originally announced June 2024.

Comments: 7 pages, Accepted to ICLR 2024 - Tiny Track

CrossVoice: Crosslingual Prosody Preserving Cascade-S2ST using Transfer Learning

Authors: Medha Hira, Arnav Goel, Anubha Gupta

Abstract: This paper presents CrossVoice, a novel cascade-based Speech-to-Speech Translation (S2ST) system employing advanced ASR, MT, and TTS technologies with cross-lingual prosody preservation through transfer learning. We conducted comprehensive experiments comparing CrossVoice with direct-S2ST systems, showing improved BLEU scores on tasks such as Fisher Es-En, VoxPopuli Fr-En and prosody preservation… ▽ More This paper presents CrossVoice, a novel cascade-based Speech-to-Speech Translation (S2ST) system employing advanced ASR, MT, and TTS technologies with cross-lingual prosody preservation through transfer learning. We conducted comprehensive experiments comparing CrossVoice with direct-S2ST systems, showing improved BLEU scores on tasks such as Fisher Es-En, VoxPopuli Fr-En and prosody preservation on benchmark datasets CVSS-T and IndicTTS. With an average mean opinion score of 3.75 out of 4, speech synthesized by CrossVoice closely rivals human speech on the benchmark, highlighting the efficacy of cascade-based systems and transfer learning in multilingual S2ST with prosody transfer. △ Less

Submitted 18 June, 2024; v1 submitted 23 May, 2024; originally announced June 2024.

Comments: 8 pages, Accepted at ICLR 2024 - Tiny Track

Learning to Estimate System Specifications in Linear Temporal Logic using Transformers and Mamba

Authors: İlker Işık, Ebru Aydin Gol, Ramazan Gokberk Cinbis

Abstract: Temporal logic is a framework for representing and reasoning about propositions that evolve over time. It is commonly used for specifying requirements in various domains, including hardware and software systems, as well as robotics. Specification mining or formula generation involves extracting temporal logic formulae from system traces and has numerous applications, such as detecting bugs and imp… ▽ More Temporal logic is a framework for representing and reasoning about propositions that evolve over time. It is commonly used for specifying requirements in various domains, including hardware and software systems, as well as robotics. Specification mining or formula generation involves extracting temporal logic formulae from system traces and has numerous applications, such as detecting bugs and improving interpretability. Although there has been a surge of deep learning-based methods for temporal logic satisfiability checking in recent years, the specification mining literature has been lagging behind in adopting deep learning methods despite their many advantages, such as scalability. In this paper, we introduce autoregressive models that can generate linear temporal logic formulae from traces, towards addressing the specification mining problem. We propose multiple architectures for this task: transformer encoder-decoder, decoder-only transformer, and Mamba, which is an emerging alternative to transformer models. Additionally, we devise a metric for quantifying the distinctiveness of the generated formulae and a straightforward algorithm to enforce the syntax constraints. Our experiments show that the proposed architectures yield promising results, generating correct and distinct formulae at a fraction of the compute cost needed for the combinatorial baseline. △ Less

Submitted 31 May, 2024; originally announced May 2024.

Comments: 20 pages, 15 figures

Leveraging Open-Source Large Language Models for encoding Social Determinants of Health using an Intelligent Router

Authors: Akul Goel, Surya Narayanan Hari, Belinda Waltman, Matt Thomson

Abstract: Social Determinants of Health (SDOH) play a significant role in patient health outcomes. The Center of Disease Control (CDC) introduced a subset of ICD-10 codes called Z-codes in an attempt to officially recognize and measure SDOH in the health care system. However, these codes are rarely annotated in a patient's Electronic Health Record (EHR), and instead, in many cases, need to be inferred from… ▽ More Social Determinants of Health (SDOH) play a significant role in patient health outcomes. The Center of Disease Control (CDC) introduced a subset of ICD-10 codes called Z-codes in an attempt to officially recognize and measure SDOH in the health care system. However, these codes are rarely annotated in a patient's Electronic Health Record (EHR), and instead, in many cases, need to be inferred from clinical notes. Previous research has shown that large language models (LLMs) show promise on extracting unstructured data from EHRs. However, with thousands of models to choose from with unique architectures and training sets, it's difficult to choose one model that performs the best on coding tasks. Further, clinical notes contain trusted health information making the use of closed-source language models from commercial vendors difficult, so the identification of open source LLMs that can be run within health organizations and exhibits high performance on SDOH tasks is an urgent problem. Here, we introduce an intelligent routing system for SDOH coding that uses a language model router to direct medical record data to open source LLMs that demonstrate optimal performance on specific SDOH codes. The intelligent routing system exhibits state of the art performance of 97.4% accuracy averaged across 5 codes, including homelessness and food insecurity, on par with closed models such as GPT-4o. In order to train the routing system and validate models, we also introduce a synthetic data generation and validation paradigm to increase the scale of training data without needing privacy protected medical records. Together, we demonstrate an architecture for intelligent routing of inputs to task-optimal language models to achieve high performance across a set of medical coding sub-tasks. △ Less

Submitted 29 May, 2024; originally announced May 2024.

Navigating AI Fallibility: Examining People's Reactions and Perceptions of AI after Encountering Personality Misrepresentations

Authors: Qiaosi Wang, Chidimma L. Anyi, Vedant Das Swain, Ashok K. Goel

Abstract: Many hyper-personalized AI systems profile people's characteristics (e.g., personality traits) to provide personalized recommendations. These systems are increasingly used to facilitate interactions among people, such as providing teammate recommendations. Despite improved accuracy, such systems are not immune to errors when making inferences about people's most personal traits. These errors manif… ▽ More Many hyper-personalized AI systems profile people's characteristics (e.g., personality traits) to provide personalized recommendations. These systems are increasingly used to facilitate interactions among people, such as providing teammate recommendations. Despite improved accuracy, such systems are not immune to errors when making inferences about people's most personal traits. These errors manifested as AI misrepresentations. However, the repercussions of such AI misrepresentations are unclear, especially on people's reactions and perceptions of the AI. We present two studies to examine how people react and perceive the AI after encountering personality misrepresentations in AI-facilitated team matching in a higher education context. Through semi-structured interviews (n=20) and a survey experiment (n=198), we pinpoint how people's existing and newly acquired AI knowledge could shape their perceptions and reactions of the AI after encountering AI misrepresentations. Specifically, we identified three rationales that people adopted through knowledge acquired from AI (mis)representations: AI works like a machine, human, and/or magic. These rationales are highly connected to people's reactions of over-trusting, rationalizing, and forgiving of AI misrepresentations. Finally, we found that people's existing AI knowledge, i.e., AI literacy, could moderate people's changes in their trust in AI after encountering AI misrepresentations, but not changes in people's social perceptions of AI. We discuss the role of people's AI knowledge when facing AI fallibility and implications for designing responsible mitigation and repair strategies. △ Less

Submitted 25 May, 2024; originally announced May 2024.

Comments: 37 pages, 11 figures

ACM Class: I.2.0

Exploring Ordinality in Text Classification: A Comparative Study of Explicit and Implicit Techniques

Authors: Siva Rajesh Kasa, Aniket Goel, Karan Gupta, Sumegh Roychowdhury, Anish Bhanushali, Nikhil Pattisapu, Prasanna Srinivasa Murthy

Abstract: Ordinal Classification (OC) is a widely encountered challenge in Natural Language Processing (NLP), with applications in various domains such as sentiment analysis, rating prediction, and more. Previous approaches to tackle OC have primarily focused on modifying existing or creating novel loss functions that \textbf{explicitly} account for the ordinal nature of labels. However, with the advent of… ▽ More Ordinal Classification (OC) is a widely encountered challenge in Natural Language Processing (NLP), with applications in various domains such as sentiment analysis, rating prediction, and more. Previous approaches to tackle OC have primarily focused on modifying existing or creating novel loss functions that \textbf{explicitly} account for the ordinal nature of labels. However, with the advent of Pretrained Language Models (PLMs), it became possible to tackle ordinality through the \textbf{implicit} semantics of the labels as well. This paper provides a comprehensive theoretical and empirical examination of both these approaches. Furthermore, we also offer strategic recommendations regarding the most effective approach to adopt based on specific settings. △ Less

Submitted 20 May, 2024; originally announced May 2024.

Comments: Findings of ACL 2024

Jill Watson: A Virtual Teaching Assistant powered by ChatGPT

Authors: Karan Taneja, Pratyusha Maiti, Sandeep Kakar, Pranav Guruprasad, Sanjeev Rao, Ashok K. Goel

Abstract: Conversational AI agents often require extensive datasets for training that are not publicly released, are limited to social chit-chat or handling a specific domain, and may not be easily extended to accommodate the latest advances in AI technologies. This paper introduces Jill Watson, a conversational Virtual Teaching Assistant (VTA) leveraging the capabilities of ChatGPT. Jill Watson based on Ch… ▽ More Conversational AI agents often require extensive datasets for training that are not publicly released, are limited to social chit-chat or handling a specific domain, and may not be easily extended to accommodate the latest advances in AI technologies. This paper introduces Jill Watson, a conversational Virtual Teaching Assistant (VTA) leveraging the capabilities of ChatGPT. Jill Watson based on ChatGPT requires no prior training and uses a modular design to allow the integration of new APIs using a skill-based architecture inspired by XiaoIce. Jill Watson is also well-suited for intelligent textbooks as it can process and converse using multiple large documents. We exclusively utilize publicly available resources for reproducibility and extensibility. Comparative analysis shows that our system outperforms the legacy knowledge-based Jill Watson as well as the OpenAI Assistants service. We employ many safety measures that reduce instances of hallucinations and toxicity. The paper also includes real-world examples from a classroom setting that demonstrate different features of Jill Watson and its effectiveness. △ Less

Submitted 17 May, 2024; originally announced May 2024.

From Human Judgements to Predictive Models: Unravelling Acceptability in Code-Mixed Sentences

Authors: Prashant Kodali, Anmol Goel, Likhith Asapu, Vamshi Krishna Bonagiri, Anirudh Govil, Monojit Choudhury, Ponnurangam Kumaraguru, Manish Shrivastava

Abstract: Current computational approaches for analysing or generating code-mixed sentences do not explicitly model ``naturalness'' or ``acceptability'' of code-mixed sentences, but rely on training corpora to reflect distribution of acceptable code-mixed sentences. Modelling human judgement for the acceptability of code-mixed text can help in distinguishing natural code-mixed text and enable quality-contro… ▽ More Current computational approaches for analysing or generating code-mixed sentences do not explicitly model ``naturalness'' or ``acceptability'' of code-mixed sentences, but rely on training corpora to reflect distribution of acceptable code-mixed sentences. Modelling human judgement for the acceptability of code-mixed text can help in distinguishing natural code-mixed text and enable quality-controlled generation of code-mixed text. To this end, we construct Cline - a dataset containing human acceptability judgements for English-Hindi~(en-hi) code-mixed text. Cline is the largest of its kind with 16,642 sentences, consisting of samples sourced from two sources: synthetically generated code-mixed text and samples collected from online social media. Our analysis establishes that popular code-mixing metrics such as CMI, Number of Switch Points, Burstines, which are used to filter/curate/compare code-mixed corpora have low correlation with human acceptability judgements, underlining the necessity of our dataset. Experiments using Cline demonstrate that simple Multilayer Perceptron (MLP) models when trained solely using code-mixing metrics as features are outperformed by fine-tuned pre-trained Multilingual Large Language Models (MLLMs). Specifically, among Encoder models XLM-Roberta and Bernice outperform IndicBERT across different configurations. Among Encoder-Decoder models, mBART performs better than mT5, however Encoder-Decoder models are not able to outperform Encoder-only models. Decoder-only models perform the best when compared to all other MLLMS, with Llama 3.2 - 3B models outperforming similarly sized Qwen, Phi models. Comparison with zero and fewshot capabilitites of ChatGPT show that MLLMs fine-tuned on larger data outperform ChatGPT, providing scope for improvement in code-mixed tasks. Zero-shot transfer from En-Hi to En-Te acceptability judgments are better than random baselines. △ Less

Submitted 5 May, 2025; v1 submitted 9 May, 2024; originally announced May 2024.

Advancing Multimodal Medical Capabilities of Gemini

Authors: Lin Yang, Shawn Xu, Andrew Sellergren, Timo Kohlberger, Yuchen Zhou, Ira Ktena, Atilla Kiraly, Faruk Ahmed, Farhad Hormozdiari, Tiam Jaroensri, Eric Wang, Ellery Wulczyn, Fayaz Jamil, Theo Guidroz, Chuck Lau, Siyuan Qiao, Yun Liu, Akshay Goel, Kendall Park, Arnav Agharwal, Nick George, Yang Wang, Ryutaro Tanno, David G. T. Barrett, Wei-Hung Weng , et al. (22 additional authors not shown)

Abstract: Many clinical tasks require an understanding of specialized data, such as medical images and genomics, which is not typically found in general-purpose large multimodal models. Building upon Gemini's multimodal models, we develop several models within the new Med-Gemini family that inherit core capabilities of Gemini and are optimized for medical use via fine-tuning with 2D and 3D radiology, histop… ▽ More Many clinical tasks require an understanding of specialized data, such as medical images and genomics, which is not typically found in general-purpose large multimodal models. Building upon Gemini's multimodal models, we develop several models within the new Med-Gemini family that inherit core capabilities of Gemini and are optimized for medical use via fine-tuning with 2D and 3D radiology, histopathology, ophthalmology, dermatology and genomic data. Med-Gemini-2D sets a new standard for AI-based chest X-ray (CXR) report generation based on expert evaluation, exceeding previous best results across two separate datasets by an absolute margin of 1% and 12%, where 57% and 96% of AI reports on normal cases, and 43% and 65% on abnormal cases, are evaluated as "equivalent or better" than the original radiologists' reports. We demonstrate the first ever large multimodal model-based report generation for 3D computed tomography (CT) volumes using Med-Gemini-3D, with 53% of AI reports considered clinically acceptable, although additional research is needed to meet expert radiologist reporting quality. Beyond report generation, Med-Gemini-2D surpasses the previous best performance in CXR visual question answering (VQA) and performs well in CXR classification and radiology VQA, exceeding SoTA or baselines on 17 of 20 tasks. In histopathology, ophthalmology, and dermatology image classification, Med-Gemini-2D surpasses baselines across 18 out of 20 tasks and approaches task-specific model performance. Beyond imaging, Med-Gemini-Polygenic outperforms the standard linear polygenic risk score-based approach for disease risk prediction and generalizes to genetically correlated diseases for which it has never been trained. Although further development and evaluation are necessary in the safety-critical medical domain, our results highlight the potential of Med-Gemini across a wide range of medical tasks. △ Less

Submitted 6 May, 2024; originally announced May 2024.

Audio Dialogues: Dialogues dataset for audio and music understanding

Authors: Arushi Goel, Zhifeng Kong, Rafael Valle, Bryan Catanzaro

Abstract: Existing datasets for audio understanding primarily focus on single-turn interactions (i.e. audio captioning, audio question answering) for describing audio in natural language, thus limiting understanding audio via interactive dialogue. To address this gap, we introduce Audio Dialogues: a multi-turn dialogue dataset containing 163.8k samples for general audio sounds and music. In addition to dial… ▽ More Existing datasets for audio understanding primarily focus on single-turn interactions (i.e. audio captioning, audio question answering) for describing audio in natural language, thus limiting understanding audio via interactive dialogue. To address this gap, we introduce Audio Dialogues: a multi-turn dialogue dataset containing 163.8k samples for general audio sounds and music. In addition to dialogues, Audio Dialogues also has question-answer pairs to understand and compare multiple input audios together. Audio Dialogues leverages a prompting-based approach and caption annotations from existing datasets to generate multi-turn dialogues using a Large Language Model (LLM). We evaluate existing audio-augmented large language models on our proposed dataset to demonstrate the complexity and applicability of Audio Dialogues. Our code for generating the dataset will be made publicly available. Detailed prompts and generated dialogues can be found on the demo website https://audiodialogues.github.io/. △ Less

Submitted 11 April, 2024; originally announced April 2024.

Comments: Demo website: https://audiodialogues.github.io/

Socratic Reasoning Improves Positive Text Rewriting

Authors: Anmol Goel, Nico Daheim, Christian Montag, Iryna Gurevych

Abstract: Reframing a negative into a positive thought is at the crux of several cognitive approaches to mental health and psychotherapy that could be made more accessible by large language model-based solutions. Such reframing is typically non-trivial and requires multiple rationalization steps to uncover the underlying issue of a negative thought and transform it to be more positive. However, this rationa… ▽ More Reframing a negative into a positive thought is at the crux of several cognitive approaches to mental health and psychotherapy that could be made more accessible by large language model-based solutions. Such reframing is typically non-trivial and requires multiple rationalization steps to uncover the underlying issue of a negative thought and transform it to be more positive. However, this rationalization process is currently neglected by both datasets and models which reframe thoughts in one step. In this work, we address this gap by augmenting open-source datasets for positive text rewriting with synthetically-generated Socratic rationales using a novel framework called \textsc{SocraticReframe}. SocraticReframe uses a sequence of question-answer pairs to rationalize the thought rewriting process. We show that such Socratic rationales significantly improve positive text rewriting for different open-source LLMs according to both automatic and human evaluations guided by criteria from psychotherapy research. We validate our framework and the synthetic rationalizations with expert judgements from domain experts and psychology students in an IRB-approved annotation study. Our findings highlight the potential of utilizing the synergy between LLM reasoning and established psychotherapy techniques to build assistive solutions for reframing negative thoughts. △ Less

Submitted 20 March, 2025; v1 submitted 5 March, 2024; originally announced March 2024.

LLMGuard: Guarding Against Unsafe LLM Behavior

Authors: Shubh Goyal, Medha Hira, Shubham Mishra, Sukriti Goyal, Arnav Goel, Niharika Dadu, Kirushikesh DB, Sameep Mehta, Nishtha Madaan

Abstract: Although the rise of Large Language Models (LLMs) in enterprise settings brings new opportunities and capabilities, it also brings challenges, such as the risk of generating inappropriate, biased, or misleading content that violates regulations and can have legal concerns. To alleviate this, we present "LLMGuard", a tool that monitors user interactions with an LLM application and flags content aga… ▽ More Although the rise of Large Language Models (LLMs) in enterprise settings brings new opportunities and capabilities, it also brings challenges, such as the risk of generating inappropriate, biased, or misleading content that violates regulations and can have legal concerns. To alleviate this, we present "LLMGuard", a tool that monitors user interactions with an LLM application and flags content against specific behaviours or conversation topics. To do this robustly, LLMGuard employs an ensemble of detectors. △ Less

Submitted 27 February, 2024; originally announced March 2024.

Comments: accepted in demonstration track of AAAI-24