Publications (23)
Interpretable Mixture of Experts
Aya Abdelsalam Ismail, Sercan Ã. Arik, Jinsung Yoon +3
Grounding and Evaluation for Large Language Models: Practical Challenges and Lessons Learned (Survey)
Krishnaram Kenthapadi, Mehrnoosh Sameki, Ankur Taly
Axiomatic Attribution for Deep Networks
Mukund Sundararajan, Ankur Taly, Qiqi Yan
Speculative RAG: Enhancing Retrieval Augmented Generation through Drafting
Zilong Wang, Zifeng Wang, Long Le +9
An Efficient Rehearsal Scheme for Catastrophic Forgetting Mitigation during Multi-stage Fine-tuning
Andrew Bai, Chih-Kuan Yeh, Cho-Jui Hsieh +1
Identifying and Mitigating the Security Risks of Generative AI
Clark Barrett, Brad Boyd, Elie Burzstein +20
A Multistakeholder Approach Towards Evaluating AI Transparency Mechanisms
Ana Lucic, Madhulika Srikumar, Umang Bhatt +4
Abductive Matching in Question Answering
Kedar Dhamdhere, Kevin S. McCurley, Mukund Sundararajan +1
Gemini 2.5: Pushing the Frontier with Advanced Reasoning, Multimodality, Long Context, and Next Generation Agentic Capabilities
Gheorghe Comanici, Eric Bieber, Mike Schaekermann +3431
Sufficient Context: A New Lens on Retrieval Augmented Generation Systems
Hailey Joren, Jianyi Zhang, Chun-Sung Ferng +3
Gradients of Counterfactuals
Mukund Sundararajan, Ankur Taly, Qiqi Yan
Explainable Machine Learning in Deployment
Umang Bhatt, Alice Xiang, Shubham Sharma +7
The Explanation Game: Explaining Machine Learning Models Using Shapley Values
Luke Merrick, Ankur Taly
First is Better Than Last for Language Data Influence
Chih-Kuan Yeh, Ankur Taly, Mukund Sundararajan +2
Counterfactual Fairness in Text Classification through Robustness
Sahaj Garg, Vincent Perot, Nicole Limtiaco +3
It was the training data pruning too!
Pramod Kaushik Mudrakarta, Ankur Taly, Mukund Sundararajan +1
Property Inference for Deep Neural Networks
Divya Gopinath, Hayes Converse, Corina S. Pasareanu +1
Using Attribution to Decode Dataset Bias in Neural Network Models for Chemistry
Kevin McCloskey, Ankur Taly, Federico Monti +2
A Note about: Local Explanation Methods for Deep Neural Networks lack Sensitivity to Parameter Values
Mukund Sundararajan, Ankur Taly
Local Explanations via Necessity and Sufficiency: Unifying Theory and Practice
David Watson, Limor Gultchin, Ankur Taly +1
Did the Model Understand the Question?
Pramod Kaushik Mudrakarta, Ankur Taly, Mukund Sundararajan +1
Privacy, Discovery, and Authentication for the Internet of Things
David J. Wu, Ankur Taly, Asim Shankar +1
Distributed Authorization in Vanadium
Andres Erbsen, Asim Shankar, Ankur Taly