activity
20242026
collaborators

45 papers

cs.CV2026

The Illusion of High Utility in Safety Alignment of Text-to-Image Diffusion Models

Adeel Yousaf, Soumik Ghosh, James Beetham +2

Safety alignment of text-to-image (T2I) diffusion models aims to suppress harmful generations while preserving utility on benign prompts. Recent methods often appear to deliver hig…

cs.CL2026

The Hidden Cost of Structured Generation in LLMs: Draft-Conditioned Constrained Decoding

Avinash Reddy, Thayne T. Walker, James S. Ide +1

Large language models (LLMs) are increasingly used to generate executable outputs, JSON objects, and API calls, where a single syntax error can make the output unusable. Constraine…

cs.CL2026

Does Reasoning Preserve Alignment? On the Trustworthiness of Large Reasoning Models

Prajakta Kini, Avinash Reddy, Souradip Chakraborty +4

Instruction-tuned LLMs are increasingly converted into reasoning models through post-training to improve multi-step task performance. This conversion is usually optimized for reaso…

cs.LG2026

The Hidden Bias of Process Reward Models:PRISM for Rewarding the Right Reasoning

Aakriti Agrawal, Souradip Chakraborty, Armin Saghafian +6

Process Reward Models (PRMs) improve credit assignment for reasoning by providing step-level feedback. However, we identify a hidden bias in PRMs caused by severe imbalance in step…

cs.AI2026

OmniToM: Benchmarking Theory of Mind in LLMs via Explicit Belief Modeling

Adam Bawatneh, Sagar Sapkota, Amrit Singh Bedi +2

Theory of Mind (ToM), the ability to infer others' knowledge, intentions, and emotions, is commonly evaluated in large language models (LLMs) using end-point question answering, wh…

cs.LG2026

RL with Learnable Textual Feedback: A Bilevel Approach

Utsav Singh, Sidhaarth Sredharan, Souradip Chakraborty +1

Reinforcement learning with verifiable rewards can improve LLM reasoning, but learning remains sample-inefficient when terminal rewards are sparse. This has motivated a growing lin…