collaborators

11 papers

cs.LG2026

Frustratingly Simple Black-Box Adaptation of Language Models via Logit Bias

Ofek I. Cohen, Lior Shani, Aviv Rosenberg +3

Many organizations aim to adapt language models for internal use, both to improve performance on domain-specific tasks and to address privacy concerns around sensitive data. Howeve…

cs.LG2026

Off-Context GRPO: Learning to Reason on Hard Problems using Privileged Information

Priyank Agrawal, Ankur Samanta, Shervin Ghasemlou +4

Reinforcement learning with verifiable rewards (RLVR) improves reasoning in large language models. Yet, typical RLVR approaches fail on difficult problems: when a model cannot gene…

cs.AI2026

BayesBench: Evaluating LLM Belief Trajectories Under Multi-Turn Evidence Accumulation

Ankur Samanta, Akshayaa Magesh, Tal Lancewicki +7

Large language models (LLMs) are typically deployed in multi-turn conversations, where each turn provides new evidence that should reduce epistemic uncertainty about their environm…

cs.AI2026

Structure Enables Effective Self-Localization of Errors in LLMs

Ankur Samanta, Akshayaa Magesh, Ayush Jain +8

Self-correction in language models remains elusive. In this work, we explore whether language models can explicitly localize errors in incorrect reasoning, as a path toward buildin…

cs.AI2026

Credit Assignment with Resets in Language Model Reasoning

Ankur Samanta, Akshayaa Magesh, Ayush Jain +7

Contemporary reinforcement learning with verifiable reward methods post-train language models on multi-step reasoning by assigning a single outcome reward uniformly across all toke…

cs.LG2026

FragmentNet: Adaptive Graph Fragmentation for Graph-to-Sequence Molecular Representation Learning

Ankur Samanta, Rohan Gupta, Aditi Misra +2

Molecular representation learning methods typically tokenize molecules as individual atoms or use rigid, rule-based fragment decompositions, limiting their ability to capture meani…