Go to ACL 2025 Workshop CoNLL homepageDynamic Epistemic Friction in Dialogue
Keywords: epistemic friction, dynamic epistemic logic, common ground, dialogue modeling, vector-symbolic architectures
TL;DR: 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..
Abstract: 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, 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.
Submission Number: 142
Loading