Zhengxing Chen — accepted AI-conference papers

2025

Law of the Weakest Link: Cross Capabilities of Large Language Models

Ming Zhong, Aston Zhang, Xuewei Wang, Rui Hou, Wenhan Xiong, Chenguang Zhu +11

ICLR 2025poster

The development and evaluation of Large Language Models (LLMs) have largely focused on individual capabilities. However, this overlooks the intersection of multiple abilities across different types of expertise that are often required for real-world tasks, which we term **cross capabilities**. To sy…

Cited by 5 Source ↗PDF ↗code ↗Scholar ↗

2025

Self-Generated Critiques Boost Reward Modeling for Language Models

Yue Yu, Zhengxing Chen, Aston Zhang, Liang Tan, Chenguang Zhu, Richard Yuanzhe Pang +7

NAACL 2025long

Reward modeling is crucial for aligning large language models (LLMs) with human preferences, especially in reinforcement learning from human feedback (RLHF). However, current reward models mainly produce scalar scores and struggle to incorporate critiques in a natural language format. We hypothesize…

Cited by 20 Source ↗PDF ↗Scholar ↗