Ashwin Kalyan

48 papers A* 9Journal 29Unranked 10
YearRankTypeTitle / Venue / Authors
2026 — conf
Engagement Undermines Safety: How Stereotypes and Toxicity Shape Humor in Language Models.
EACL (Volume 1: Long Papers)
Atharvan Dogra, Soumya Suvra Ghosal, Ameet Deshpande, Ashwin Kalyan, Dinesh Manocha
2026 J jnl
RLHF Deciphered: A Critical Analysis of Reinforcement Learning from Human Feedback for LLMs.
ACM Comput. Surv.
Shreyas Chaudhari, Pranjal Aggarwal, Vishvak Murahari, Tanmay Rajpurohit, Ashwin Kalyan, Karthik Narasimhan, Ameet Deshpande, Bruno Castro da Silva
2025 J jnl
Agent Context Protocols Enhance Collective Inference.
CoRR
Devansh Bhardwaj, Arjun Beniwal, Shreyas Chaudhari, Ashwin Kalyan, Tanmay Rajpurohit, Karthik R. Narasimhan, Ameet Deshpande, Vishvak Murahari
2025 J jnl
Engagement Undermines Safety: How Stereotypes and Toxicity Shape Humor in Language Models.
CoRR
Atharvan Dogra, Soumya Suvra Ghosal, Ameet Deshpande, Ashwin Kalyan, Dinesh Manocha
2025 — conf
Language Models can Subtly Deceive Without Lying: A Case Study on Strategic Phrasing in Legislation.
ACL (1)
Atharvan Dogra, Krishna Pillutla, Ameet Deshpande, Ananya B. Sai, John J. Nay, Tanmay Rajpurohit, Ashwin Kalyan, Balaraman Ravindran
2025 — conf
PersonaGym: Evaluating Persona Agents and LLMs.
EMNLP (Findings)
Vinay Samuel, Henry Peng Zou, Yue Zhou, Shreyas Chaudhari, Ashwin Kalyan, Tanmay Rajpurohit, Ameet Deshpande, Karthik R. Narasimhan, Vishvak Murahari
2025 J jnl
Probing AI Safety with Source Code.
CoRR
Ujwal Narayan, Shreyas Chaudhari, Ashwin Kalyan, Tanmay Rajpurohit, Karthik Narasimhan, Ameet Deshpande, Vishvak Murahari
2024 A* conf
Bias Runs Deep: Implicit Reasoning Biases in Persona-Assigned LLMs.
ICLR
Shashank Gupta, Vaishnavi Shrivastava, Ameet Deshpande, Ashwin Kalyan, Peter Clark, Ashish Sabharwal, Tushar Khot
2024 J jnl
Deception in Reinforced Autonomous Agents: The Unconventional Rabbit Hat Trick in Legislation.
CoRR
Atharvan Dogra, Ameet Deshpande, John J. Nay, Tanmay Rajpurohit, Ashwin Kalyan, Balaraman Ravindran
2024 A* conf
GEO: Generative Engine Optimization.
KDD
Pranjal Aggarwal, Vishvak Murahari, Tanmay Rajpurohit, Ashwin Kalyan, Karthik Narasimhan, Ameet Deshpande
2024 J jnl
PersonaGym: Evaluating Persona Agents and LLMs.
CoRR
Vinay Samuel, Henry Peng Zou, Yue Zhou, Shreyas Chaudhari, Ashwin Kalyan, Tanmay Rajpurohit, Ameet Deshpande, Karthik Narasimhan, Vishvak Murahari
2024 — conf
QualEval: Qualitative Evaluation for Model Improvement.
NAACL-HLT
Vishvak Murahari, Ameet Deshpande, Peter Clark, Tanmay Rajpurohit, Ashish Sabharwal, Karthik Narasimhan, Ashwin Kalyan
2024 J jnl
RLHF Deciphered: A Critical Analysis of Reinforcement Learning from Human Feedback for LLMs.
CoRR
Shreyas Chaudhari, Pranjal Aggarwal, Vishvak Murahari, Tanmay Rajpurohit, Ashwin Kalyan, Karthik Narasimhan, Ameet Deshpande, Bruno Castro da Silva
2023 J jnl
Anthropomorphization of AI: Opportunities and Risks.
CoRR
Ameet Deshpande, Tanmay Rajpurohit, Karthik Narasimhan, Ashwin Kalyan
2023 J jnl
Bias Runs Deep: Implicit Reasoning Biases in Persona-Assigned LLMs.
CoRR
Shashank Gupta, Vaishnavi Shrivastava, Ameet Deshpande, Ashwin Kalyan, Peter Clark, Ashish Sabharwal, Tushar Khot
2023 A* conf
C-STS: Conditional Semantic Textual Similarity.
EMNLP
Ameet Deshpande, Carlos E. Jimenez, Howard Chen, Vishvak Murahari, Victoria Graf, Tanmay Rajpurohit, Ashwin Kalyan, Danqi Chen, Karthik Narasimhan
2023 J jnl
CSTS: Conditional Semantic Textual Similarity.
CoRR
Ameet Deshpande, Carlos E. Jimenez, Howard Chen, Vishvak Murahari, Victoria Graf, Tanmay Rajpurohit, Ashwin Kalyan, Danqi Chen, Karthik Narasimhan
2023 J jnl
Distraction-free Embeddings for Robust VQA.
CoRR
Atharvan Dogra, Deeksha Varshney, Ashwin Kalyan, Ameet Deshpande, Neeraj Kumar
2023 A* conf
Dynamic Prompt Learning via Policy Gradient for Semi-structured Mathematical Reasoning.
ICLR
Pan Lu, Liang Qiu, Kai-Wei Chang, Ying Nian Wu, Song-Chun Zhu, Tanmay Rajpurohit, Peter Clark, Ashwin Kalyan
2023 J jnl
Estimating Numbers without Regression.
CoRR
Avijit Thawani, Jay Pujara, Ashwin Kalyan
2023 J jnl
Exploiting Generalization in Offline Reinforcement Learning via Unseen State Augmentations.
CoRR
Nirbhay Modhe, Qiaozi Gao, Ashwin Kalyan, Dhruv Batra, Govind Thattai, Gaurav S. Sukhatme
2023 J jnl
GEO: Generative Engine Optimization.
CoRR
Pranjal Aggarwal, Vishvak Murahari, Tanmay Rajpurohit, Ashwin Kalyan, Karthik R. Narasimhan, Ameet Deshpande
2023 A* conf
Let GPT be a Math Tutor: Teaching Math Word Problem Solvers with Customized Exercise Generation.
EMNLP
Zhenwen Liang, Wenhao Yu, Tanmay Rajpurohit, Peter Clark, Xiangliang Zhang, Ashwin Kalyan
2023 J jnl
Let GPT be a Math Tutor: Teaching Math Word Problem Solvers with Customized Exercise Generation.
CoRR
Zhenwen Liang, Wenhao Yu, Tanmay Rajpurohit, Peter Clark, Xiangliang Zhang, Ashwin Kalyan
2023 J jnl
ProKnow: Process Knowledge for Safety Constrained and Explainable Question Generation for Mental Health Diagnostic Assistance.
CoRR
Kaushik Roy, Manas Gaur, Misagh Soltani, Vipula Rawte, Ashwin Kalyan, Amit P. Sheth
2023 J jnl
QualEval: Qualitative Evaluation for Model Improvement.
CoRR
Vishvak Murahari, Ameet Deshpande, Peter Clark, Tanmay Rajpurohit, Ashish Sabharwal, Karthik Narasimhan, Ashwin Kalyan
2023 — conf
RL4F: Generating Natural Language Feedback with Reinforcement Learning for Repairing Model Outputs.
ACL (1)
Afra Feyza Akyürek, Ekin Akyürek, Ashwin Kalyan, Peter Clark, Derry Tanti Wijaya, Niket Tandon
2023 J jnl
RL4F: Generating Natural Language Feedback with Reinforcement Learning for Repairing Model Outputs.
CoRR
Afra Feyza Akyürek, Ekin Akyürek, Aman Madaan, Ashwin Kalyan, Peter Clark, Derry Wijaya, Niket Tandon
2023 J jnl
Toxicity in ChatGPT: Analyzing Persona-assigned Language Models.
CoRR
Ameet Deshpande, Vishvak Murahari, Tanmay Rajpurohit, Ashwin Kalyan, Karthik Narasimhan
2023 — conf
Toxicity in chatgpt: Analyzing persona-assigned language models.
EMNLP (Findings)
Ameet Deshpande, Vishvak Murahari, Tanmay Rajpurohit, Ashwin Kalyan, Karthik Narasimhan
2022 J jnl
Dynamic Prompt Learning via Policy Gradient for Semi-structured Mathematical Reasoning.
CoRR
Pan Lu, Liang Qiu, Kai-Wei Chang, Ying Nian Wu, Song-Chun Zhu, Tanmay Rajpurohit, Peter Clark, Ashwin Kalyan
2022 A* conf
LILA: A Unified Benchmark for Mathematical Reasoning.
EMNLP
Swaroop Mishra, Matthew Finlayson, Pan Lu, Leonard Tang, Sean Welleck, Chitta Baral, Tanmay Rajpurohit, Oyvind Tafjord, Ashish Sabharwal, Peter Clark, Ashwin Kalyan
2022 A* conf
Learn to Explain: Multimodal Reasoning via Thought Chains for Science Question Answering.
NeurIPS
Pan Lu, Swaroop Mishra, Tanglin Xia, Liang Qiu, Kai-Wei Chang, Song-Chun Zhu, Oyvind Tafjord, Peter Clark, Ashwin Kalyan
2022 J jnl
Learn to Explain: Multimodal Reasoning via Thought Chains for Science Question Answering.
CoRR
Pan Lu, Swaroop Mishra, Tony Xia, Liang Qiu, Kai-Wei Chang, Song-Chun Zhu, Oyvind Tafjord, Peter Clark, Ashwin Kalyan
2022 J jnl
Lila: A Unified Benchmark for Mathematical Reasoning.
CoRR
Swaroop Mishra, Matthew Finlayson, Pan Lu, Leonard Tang, Sean Welleck, Chitta Baral, Tanmay Rajpurohit, Oyvind Tafjord, Ashish Sabharwal, Peter Clark, Ashwin Kalyan
2022 — conf
NumGLUE: A Suite of Fundamental yet Challenging Mathematical Reasoning Tasks.
ACL (1)
Swaroop Mishra, Arindam Mitra, Neeraj Varshney, Bhavdeep Singh Sachdeva, Peter Clark, Chitta Baral, Ashwin Kalyan
2022 J jnl
NumGLUE: A Suite of Fundamental yet Challenging Mathematical Reasoning Tasks.
CoRR
Swaroop Mishra, Arindam Mitra, Neeraj Varshney, Bhavdeep Singh Sachdeva, Peter Clark, Chitta Baral, Ashwin Kalyan
2022 J jnl
ProKnow: Process knowledge for safety constrained and explainable question generation for mental health diagnostic assistance.
Frontiers Big Data
Kaushik Roy, Manas Gaur, Misagh Soltani, Vipula Rawte, Ashwin Kalyan, Amit P. Sheth
2022 J jnl
SPARTAN: Sparse Hierarchical Memory for Parameter-Efficient Transformers.
CoRR
Ameet Deshpande, Md. Arafat Sultan, Anthony Ferritto, Ashwin Kalyan, Karthik Narasimhan, Avirup Sil
2021 J jnl
How Much Coffee Was Consumed During EMNLP 2019? Fermi Problems: A New Reasoning Challenge for AI.
CoRR
Ashwin Kalyan, Abhinav Kumar, Arjun Chandrasekaran, Ashish Sabharwal, Peter Clark
2021 — conf
How much coffee was consumed during EMNLP 2019? Fermi Problems: A New Reasoning Challenge for AI.
EMNLP (1)
Ashwin Kalyan, Abhinav Kumar, Arjun Chandrasekaran, Ashish Sabharwal, Peter Clark
2021 J jnl
Model-Advantage Optimization for Model-Based Reinforcement Learning.
CoRR
Nirbhay Modhe, Harish Kamath, Dhruv Batra, Ashwin Kalyan
2021 — conf
Programming Puzzles.
NeurIPS Datasets and Benchmarks
Tal Schuster, Ashwin Kalyan, Alex Polozov, Adam Kalai
2021 J jnl
Programming Puzzles.
CoRR
Tal Schuster, Ashwin Kalyan, Oleksandr Polozov, Adam Tauman Kalai
2019 A* conf
Trainable Decoding of Sets of Sequences for Neural Sequence Models.
ICML
Ashwin Kalyan, Peter Anderson, Stefan Lee, Dhruv Batra
2018 A* conf
Learn from Your Neighbor: Learning Multi-modal Mappings from Sparse Annotations.
ICML
Ashwin Kalyan, Stefan Lee, Anitha Kannan, Dhruv Batra
2018 J jnl
Learn from Your Neighbor: Learning Multi-modal Mappings from Sparse Annotations.
CoRR
Ashwin Kalyan, Stefan Lee, Anitha Kannan, Dhruv Batra
2018 — conf
Neural-Guided Deductive Search for Real-Time Program Synthesis from Examples.
ICLR (Poster)
Ashwin Kalyan, Abhishek Mohta, Oleksandr Polozov, Dhruv Batra, Prateek Jain, Sumit Gulwani