collaborators

7 papers

cs.CL2026

Continual Memorization of Factoids in Language Models

Howard Chen, Jiayi Geng, Adithya Bhaskar +2

As new knowledge rapidly accumulates, language models (LMs) with pretrained knowledge quickly become obsolete. A common approach to updating LMs is fine-tuning them directly on new…

cs.CL2026

Self-Distillation Zero: Self-Revision Turns Binary Rewards into Dense Supervision

Yinghui He, Simran Kaur, Adithya Bhaskar +7

Current post-training methods in verifiable settings fall into two categories. Reinforcement learning (RLVR) relies on binary rewards, which are broadly applicable and powerful, bu…

cs.CL2025

Extracting Rule-based Descriptions of Attention Features in Transformers

Dan Friedman, Adithya Bhaskar, Alexander Wettig +1

Mechanistic interpretability strives to explain model behavior in terms of bottom-up primitives. The leading paradigm is to express hidden states as a sparse linear combination of…

cs.CL2025

Language Models that Think, Chat Better

Adithya Bhaskar, Xi Ye, Danqi Chen

Reinforcement learning with verifiable rewards (RLVR) trains language models to use long chain-of-thought reasoning (CoT) in domains like mathematics and code with rule-based verif…

cs.CL2025

Cache Me If You Can: How Many KVs Do You Need for Effective Long-Context LMs?

Adithya Bhaskar, Alexander Wettig, Tianyu Gao +2

Language models handle increasingly long contexts for tasks such as book summarization, but this leads to growing memory costs for the key-value (KV) cache. Many prior works have p…

cs.LG2025

Unintentional Unalignment: Likelihood Displacement in Direct Preference Optimization

Noam Razin, Sadhika Malladi, Adithya Bhaskar +3

Direct Preference Optimization (DPO) and its variants are increasingly used for aligning language models with human preferences. Although these methods are designed to teach a mode…