提出对话中信念更新的阻力机制，提升AI对人类认知冲突的理解。
Dynamic Epistemic Friction in Dialogue
- 用动态认识逻辑建模对话中的信念更新阻力
- 实验证明该模型能有效预测对话中的信念变化
- 适合研究人机协作与认知对齐的学者
大型语言模型在对齐人类偏好方面取得进展，但常忽视“认识摩擦”——即面对新矛盾或模糊信息时信念更新的内在阻力。本文将动态认识摩擦定义为信念状态与外部证据支持的新命题之间的不一致，并基于动态认识逻辑框架，揭示其在交互中表现为非平凡的信念修正过程。通过情境化协作任务分析，证明该模型可有效预测对话中的信念更新；进一步探讨了将信念对齐作为认识阻力度量的方法如何适应现实对话的复杂性。
原文摘要 · Abstract (English)
Recent developments in aligning Large Language Models (LLMs) with human preferences have significantly enhanced their utility in human-AI collaborative scenarios. However, such approaches often neglect the critical role of "epistemic friction," or the inherent resistance encountered when updating beliefs in response to new, conflicting, or ambiguous information. In this paper, we define dynamic epistemic friction as the resistance to epistemic integration, characterized by the misalignment between an agent's current belief state and new propositions supported by external evidence. We position this within the framework of Dynamic Epistemic Logic (Van Benthem and Pacuit, 2011), where friction emerges as nontrivial belief-revision during the interaction. We then present analyses from a situated collaborative task that demonstrate how this model of epistemic friction can effectively predict belief updates in dialogues, and we subsequently discuss how the model of belief alignment as a measure of epistemic resistance or friction can naturally be made more sophisticated to accommodate the complexities of real-world dialogue scenarios.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。