collaborators

6 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.SD2026

When Scaling Fails: Mitigating Audio Perception Decay of LALMs via Multi-Step Perception-Aware Reasoning

Ruixiang Mao, Xiangnan Ma, Dan Chen +12

Test-Time Scaling has shown notable efficacy in addressing complex problems through scaling inference compute. However, within Large Audio-Language Models (LALMs), an unintuitive p…

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.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…

cs.CL2025

Representing Rule-based Chatbots with Transformers

Dan Friedman, Abhishek Panigrahi, Danqi Chen

What kind of internal mechanisms might Transformers use to conduct fluid, natural-sounding conversations? Prior work has illustrated by construction how Transformers can solve vari…