作者位次 #3/6ACL 2026Findings· Findings of ACL
Beyond Evidence: Belief-Chain Conditioning for Persuasive Misinformation Debunking Explanation
Yi-Li Hsu · Li-Wun Chang · Chun-Yu Hsu · Wei-Kuan Shih · Aiping Xiong · Lun-Wei Ku
摘要
As AI systems increasingly mediate everyday communication, large language models (LLMs) are expected not only to provide factually accurate responses but also to generate explanations that engage with users’ mental states. We build on the concept of cognitive chains—structured representations of...