Zhong-Tian Hua

FRAME: Faithful Multi-Agent Fact Checking via Hierarchical Gating and Bayesian-Inspired Evidence-Conflict Perception

Fact checking is a key task in the field of natural language processing, and aims to judge the authenticity of a given claim by using external evidence. Existing multi-agent-based fact-checking systems achieve significant improvements on multiple benchmark datasets, but still have two core limitations: firstly, they la...