Lune

ACL Findings2026

Beyond Evidence: Belief-Chain Conditioning for Persuasive Misinformation Debunking Explanation

Yi-Li Hsu, Li-Wun Chang, Chun-Yu Hsu, Jane Wei-Kuan Shih, Aiping Xiong, Lun-Wei Ku

Abstract

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 Situation, Clue, Thought, Action, and Emotion inspired by Theory of Mind-to investigate whether conditioning LLM outputs on such belief chains improves explanation quality. Specifically, we evaluate explanations along six reader-perceived dimensions: overall quality, logical correctness, completeness, conciseness, empathy, and agreement. Prior work shows that LLM explanations often default to neutral or uncertain stances, while individuals holding strong false beliefs remain highly resistant to correction. To address this challenge, we instantiate cognitive chains from two perspectives: believers and non-believers of the news claims. Using GPT-4.1 as a role-player across these stances, we find that incorporating believers' chains improves the perceived quality of explanations for audiences with misinformationaligned beliefs. Our findings underscore the importance of modeling diverse mental states in explanation generation and provide the first systematic evidence that Theory-of-Mind-based cognitive chains enhance the persuasiveness of explanations in misinformation contexts.

Ask Lune

Know this paper in minutes, not an afternoon.

Lune can read every page of it and the top-tier papers that cite it, and gives you its claims, its evidence and its limits, each one cited to the paper it comes from. No skimming, no AI slop.

Questions to start from

Lune can draw on

the full paper · related work

Get the answer

Free to start. No credit card required.

Lineage

Builds onCited byLeft to right by year; the more cited, the higher.

Builds on2

  1. Generating Fact Checking ExplanationsPepa Atanasova, Jakob Grue Simonsen, Christina Lioma, Isabelle AugensteinACL 2020 · 130 citations
  2. Evaluating the Factual Consistency of Abstractive Text SummarizationWojciech Kryscinski, Bryan McCann, Caiming Xiong, Richard SocherEMNLP 2020 · 67 citations

Related papers

  1. Do Models Explain Themselves? Counterfactual Simulatability of Natural Language ExplanationsYanda Chen, Ruiqi Zhong, Narutatsu Ri, Chen Zhao et al.ICML 2024 · 90 citations
  2. Deceptive Explanations by Large Language Models Lead People to Change their Beliefs About Misinformation More Often than Honest ExplanationsValdemar Danry, Pat Pataranutaporn, Matthew Groh, Ziv EpsteinCHI 2025 · 32 citations
  3. "Can LLMs Persuade Humans with Deception?": From a Deceptive Strategy Taxonomy to a Large-Scale Empirical StudyHaein Yeo, Seungwan Jin, Taehyung Noh, Yejin Shin et al.CHI 2026 · 2 citations
  4. Sensemaking in Multi-Agent LLM Interfaces: How Users Interpret Transparency and Trustworthiness CuesSaumya Pareek, Jarod Govers, Naja Kathrine Kollerup, Emily Wong et al.CHI 2026 · 1 citation
  5. RecToM: A Benchmark for Evaluating Machine Theory of Mind in LLM-based Conversational Recommender SystemsMengfan Li, Xuanhua Shi, Yang DengAAAI 2026
Dusk over the sea between two cliffs drawn in fine vertical lines