collaborators

5 papers

cs.LG2026

LLMs as Noisy Channels: A Shannon Perspective on Model Capacity and Scaling Laws

Xu Ouyang, Deyi Liu, Yuhang Cai +5

Existing scaling laws for Large Language Models (LLMs), predominantly monotonic power laws, fail to explain emerging non-monotonic phenomena such as catastrophic overtraining and q…

cs.CL2026

ProText: A benchmark dataset for measuring (mis)gendering in long-form texts

Hadas Kotek, Margit Bowler, Patrick Sonnenberg +1

We introduce ProText, a dataset for measuring gendering and misgendering in stylistically diverse long-form English texts. ProText spans three dimensions: Theme nouns (names, occup…

cs.CL2026

The Shadow Self: Intrinsic Value Misalignment in Large Language Model Agents

Chen Chen, Kim Young Il, Yuan Yang +7

Large language model (LLM) agents with extended autonomy unlock new capabilities, but also introduce heightened challenges for LLM safety. In particular, an LLM agent may pursue ob…

cs.CL2025

GatePro: Parameter-Free Expert Selection Optimization for Mixture-of-Experts Models

Chen Zheng, Yuhang Cai, Deyi Liu +7

Modern large language models leverage Mixture-of-Experts (MoE) architectures for efficient scaling, but face a critical challenge: functionally similar experts are often selected s…

cs.CL2025

Balanced Actor Initialization: Stable RLHF Training of Distillation-Based Reasoning Models

Chen Zheng, Yiyuan Ma, Yuan Yang +11

The development of alignment and reasoning capabilities in large language models has seen remarkable progress through two paradigms: instruction tuning and reinforcement learning f…