Hongning Wang

A novel approach to reward over-optimization in language models using uncertainty estimation.

ChatGLM-RLHF improves AI interactions through human feedback and advanced training methods.

GLM-4 models show improved capabilities in language understanding and generation.

A new method to assess how well LLMs understand and apply rules.

Learn how human feedback shapes AI language model responses.

A fresh approach to enhance instruction-following in language models.