Liangming Pan

This article discusses how self-correction enhances the reliability of language models.

A study on generating meaningful follow-up questions to deepen understanding.

This article discusses the importance and obstacles in fact verification systems.

A new approach boosts language models' scientific reasoning through effective tool usage.

Investigating self-bias in LLMs and its impact on performance.

This article explores how adversaries impact teamwork among language models.

A new method improves code repair for underused programming languages.

TART enhances table reasoning tasks using specialized tools and large language models.