Ashwin Kalyan

Independent Sector — United States

Computer Science · Physical Sciences

13h-index878citations46works4.22yr avg
OpenAlex↗Google Scholar↗Lab page↗

Accepting Students?

No reports yet. Know if this professor is taking students?

Research Topics

Topic Modeling(17), Natural Language Processing Techniques(16), Software Engineering Research(6), Reinforcement Learning in Robotics(6), Ethics and Social Impacts of AI(5)

Publications46 total

Engagement Undermines Safety: How Stereotypes and Toxicity Shape Humor in Language Models
arXiv (Cornell University)·2025Open Access
Probing AI Safety with Source Code
arXiv (Cornell University)·2025Open Access
RLHF Deciphered: A Critical Analysis of Reinforcement Learning from Human Feedback for LLMs
ACM Computing Surveys·2025· 25 citedOpen Access
Agent Context Protocols Enhance Collective Inference
arXiv (Cornell University)·2025Open Access
PersonaGym: Evaluating Persona Agents and LLMs
2025· 2 citedOpen Access
Language Models can Subtly Deceive Without Lying: A Case Study on Strategic Phrasing in Legislation
2025Open Access
ProKnow: Efficacy of Process Knowledge in Safety Constrained and Explainable Question Generation for Mental Health Diagnostic Assistance
2024
GEO: Generative Engine Optimization
2024· 12 cited
PersonaGym: Evaluating Persona Agents and LLMs
arXiv (Cornell University)·2024· 3 citedOpen Access
Language Models can Subtly Deceive Without Lying: A Case Study on Strategic Phrasing in Legislation
arXiv (Cornell University)·2024Open Access
RLHF Deciphered: A Critical Analysis of Reinforcement Learning from Human Feedback for LLMs
arXiv (Cornell University)·2024· 8 citedOpen Access
QualEval: Qualitative Evaluation for Model Improvement
2024Open Access
GEO: Generative Engine Optimization
arXiv (Cornell University)·2023Open Access
Bias Runs Deep: Implicit Reasoning Biases in Persona-Assigned LLMs
arXiv (Cornell University)·2023· 9 citedOpen Access
QualEval: Qualitative Evaluation for Model Improvement
arXiv (Cornell University)·2023Open Access
Estimating Numbers without Regression
arXiv (Cornell University)·2023· 1 citedOpen Access
Distraction-free Embeddings for Robust VQA
arXiv (Cornell University)·2023Open Access
Exploiting Generalization in Offline Reinforcement Learning via Unseen State Augmentations
arXiv (Cornell University)·2023· 1 citedOpen Access
C-STS: Conditional Semantic Textual Similarity
arXiv (Cornell University)·2023· 2 citedOpen Access
Anthropomorphization of AI: Opportunities and Risks
arXiv (Cornell University)·2023· 12 citedOpen Access
page 1 of 3Next →

Frequent Co-authors

Tanmay Rajpurohit(22), Ameet Deshpande(21), Karthik Narasimhan(17), Vishvak Murahari(14), Peter Clark(10), Dhruv Batra(9), Ashish Sabharwal(6), Shreyas Chaudhari(6), Swaroop Mishra(5), Pan Lu(4), Chitta Baral(4), Oleksandr Polozov(4), Pranjal Aggarwal(4), Nirbhay Modhe(4), Atharvan Dogra(4), Oyvind Tafjord(3), Peter E. Clark(3), Stefan Lee(3), Liang Qiu(2), Kai-Wei Chang(2)