Ameet Deshpande

47 papers A* 5B 1Journal 30Unranked 11

Year	Rank	Type	Title / 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`	Abstract Reward Processes: Leveraging State Abstraction for Consistent Off-Policy Evaluation. NeurIPS Shreyas Chaudhari, Ameet Deshpande, Bruno C. da Silva, Philip S. Thomas
2024	J	`jnl`	Abstract Reward Processes: Leveraging State Abstraction for Consistent Off-Policy Evaluation. CoRR Shreyas Chaudhari, Ameet Deshpande, Bruno Castro da Silva, Philip S. Thomas
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	—	`conf`	InstructEval: Systematic Evaluation of Instruction Selection Methods. NAACL-HLT (Findings) Anirudh Ajith, Chris Pan, Mengzhou Xia, Ameet Deshpande, Karthik Narasimhan
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	J	`jnl`	GEO: Generative Engine Optimization. CoRR Pranjal Aggarwal, Vishvak Murahari, Tanmay Rajpurohit, Ashwin Kalyan, Karthik R. Narasimhan, Ameet Deshpande
2023	J	`jnl`	InstructEval: Systematic Evaluation of Instruction Selection Methods. CoRR Anirudh Ajith, Chris Pan, Mengzhou Xia, Ameet Deshpande, Karthik Narasimhan
2023	—	`conf`	MUX-PLMs: Data Multiplexing for High-throughput Language Models. EMNLP (Findings) Vishvak Murahari, Ameet Deshpande, Carlos E. Jimenez, Izhak Shafran, Mingqiu Wang, Yuan Cao, Karthik Narasimhan
2023	—	`conf`	MUX-PLMs: Pre-training Language Models with Data Multiplexing. RepL4NLP@ACL Vishvak Murahari, Ameet Deshpande, Carlos E. Jimenez, Izhak Shafran, Mingqiu Wang, Yuan Cao, Karthik Narasimhan
2023	J	`jnl`	MUX-PLMs: Pre-training Language Models with Data Multiplexing. CoRR Vishvak Murahari, Ameet Deshpande, Carlos E. Jimenez, Izhak Shafran, Mingqiu Wang, Yuan Cao, Karthik Narasimhan
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	A*	`conf`	SemSup-XC: Semantic Supervision for Zero and Few-shot Extreme Classification. ICML Pranjal Aggarwal, Ameet Deshpande, Karthik R. Narasimhan
2023	J	`jnl`	SemSup-XC: Semantic Supervision for Zero and Few-shot Extreme Classification. CoRR Pranjal Aggarwal, Ameet Deshpande, Karthik Narasimhan
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`	ALIGN-MLM: Word Embedding Alignment is Crucial for Multilingual Pre-training. CoRR Henry Tang, Ameet Deshpande, Karthik Narasimhan
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
2022	J	`jnl`	Semantic Supervision: Enabling Generalization over Output Spaces. CoRR Austin W. Hanjie, Ameet Deshpande, Karthik Narasimhan
2022	—	`conf`	When is BERT Multilingual? Isolating Crucial Ingredients for Cross-lingual Transfer. NAACL-HLT Ameet Deshpande, Partha Talukdar, Karthik Narasimhan
2021	J	`jnl`	When is BERT Multilingual? Isolating Crucial Ingredients for Cross-lingual Transfer. CoRR Ameet Deshpande, Partha Talukdar, Karthik Narasimhan
2020	J	`jnl`	CLEVR Parser: A Graph Parser Library for Geometric Learning on Language Grounded Image Scenes. CoRR Raeid Saqur, Ameet Deshpande
2020	J	`jnl`	Evaluating a Generative Adversarial Framework for Information Retrieval. CoRR Ameet Deshpande, Mitesh M. Khapra
2020	—	`conf`	Guiding Attention for Self-Supervised Learning with Transformers. EMNLP (Findings) Ameet Deshpande, Karthik Narasimhan
2020	J	`jnl`	Guiding Attention for Self-Supervised Learning with Transformers. CoRR Ameet Deshpande, Karthik Narasimhan
2020	J	`jnl`	Sentiment Analysis for Reinforcement Learning. CoRR Ameet Deshpande, Eve Fleisig
2019	B	`conf`	FigureNet : A Deep Learning model for Question-Answering on Scientific Plots. IJCNN Revanth Reddy, Rahul Ramesh, Ameet Deshpande, Mitesh M. Khapra
2019	—	`conf`	Leveraging Ontological Knowledge for Neural Language Models. COMAD/CODS Ameet Deshpande, Monisha Jegadeesan
2018	J	`jnl`	A Question-Answering framework for plots using Deep learning. CoRR Revanth Reddy, Rahul Ramesh, Ameet Deshpande, Mitesh M. Khapra
2018	J	`jnl`	Discovering hierarchies using Imitation Learning from hierarchy aware policies. CoRR Ameet Deshpande, Harshavardhan P. K, Balaraman Ravindran
2018	J	`jnl`	Improvements on Hindsight Learning. CoRR Ameet Deshpande, Srikanth Sarma
2018	J	`jnl`	Weight Initialization in Neural Language Models. CoRR Ameet Deshpande, Vedant Somani