@inproceedings{obiso-etal-2025-dynamic,
    title = "Dynamic Epistemic Friction in Dialogue",
    author = "Obiso, Timothy  and
      Lai, Kenneth  and
      Nath, Abhijnan  and
      Krishnaswamy, Nikhil  and
      Pustejovsky, James",
    editor = "Boleda, Gemma  and
      Roth, Michael",
    booktitle = "Proceedings of the 29th Conference on Computational Natural Language Learning",
    month = jul,
    year = "2025",
    address = "Vienna, Austria",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/acl25-workshop-ingestion/2025.conll-1.21/",
    pages = "323--333",
    ISBN = "979-8-89176-271-8",
    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."
}