collaborators
Showing cs.CLShow all

5 papers · 1 filter

cs.CL2026

The Realignment Problem: When Right becomes Wrong in LLMs

Aakash Sen Sharma, Debdeep Sanyal, Manodeep Ray +3

Post-training alignment of large language models (LLMs) relies on large-scale human annotations guided by policy specifications that change over time. Cultural shifts, value reinte…

cs.CL2025

Confidence is Not Competence

Debdeep Sanyal, Manya Pandey, Dhruv Kumar +2

Large language models (LLMs) often exhibit a puzzling disconnect between their asserted confidence and actual problem-solving competence. We offer a mechanistic account of this dec…

cs.CL2025

Policy Optimization Prefers The Path of Least Resistance

Debdeep Sanyal, Aakash Sen Sharma, Dhruv Kumar +2

Policy optimization (PO) algorithms are used to refine Large Language Models for complex, multi-step reasoning. Current state-of-the-art pipelines enforce a strict think-then-answe…

cs.CL2025

AntiDote: Bi-level Adversarial Training for Tamper-Resistant LLMs

Debdeep Sanyal, Manodeep Ray, Murari Mandal

The release of open-weight large language models (LLMs) creates a tension between advancing accessible research and preventing misuse, such as malicious fine-tuning to elicit harmf…

cs.CL2025

Nine Ways to Break Copyright Law and Why Our LLM Won't: A Fair Use Aligned Generation Framework

Aakash Sen Sharma, Debdeep Sanyal, Priyansh Srivastava +4

Large language models (LLMs) commonly risk copyright infringement by reproducing protected content verbatim or with insufficient transformative modifications, posing significant et…