@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://aclanthology.org/2025.conll-1.21/",
doi = "10.18653/v1/2025.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."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="obiso-etal-2025-dynamic">
<titleInfo>
<title>Dynamic Epistemic Friction in Dialogue</title>
</titleInfo>
<name type="personal">
<namePart type="given">Timothy</namePart>
<namePart type="family">Obiso</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Kenneth</namePart>
<namePart type="family">Lai</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Abhijnan</namePart>
<namePart type="family">Nath</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Nikhil</namePart>
<namePart type="family">Krishnaswamy</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">James</namePart>
<namePart type="family">Pustejovsky</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2025-07</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 29th Conference on Computational Natural Language Learning</title>
</titleInfo>
<name type="personal">
<namePart type="given">Gemma</namePart>
<namePart type="family">Boleda</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Michael</namePart>
<namePart type="family">Roth</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Vienna, Austria</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-8-89176-271-8</identifier>
</relatedItem>
<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.</abstract>
<identifier type="citekey">obiso-etal-2025-dynamic</identifier>
<identifier type="doi">10.18653/v1/2025.conll-1.21</identifier>
<location>
<url>https://aclanthology.org/2025.conll-1.21/</url>
</location>
<part>
<date>2025-07</date>
<extent unit="page">
<start>323</start>
<end>333</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Dynamic Epistemic Friction in Dialogue
%A Obiso, Timothy
%A Lai, Kenneth
%A Nath, Abhijnan
%A Krishnaswamy, Nikhil
%A Pustejovsky, James
%Y Boleda, Gemma
%Y Roth, Michael
%S Proceedings of the 29th Conference on Computational Natural Language Learning
%D 2025
%8 July
%I Association for Computational Linguistics
%C Vienna, Austria
%@ 979-8-89176-271-8
%F obiso-etal-2025-dynamic
%X 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.
%R 10.18653/v1/2025.conll-1.21
%U https://aclanthology.org/2025.conll-1.21/
%U https://doi.org/10.18653/v1/2025.conll-1.21
%P 323-333
Markdown (Informal)
[Dynamic Epistemic Friction in Dialogue](https://aclanthology.org/2025.conll-1.21/) (Obiso et al., CoNLL 2025)
ACL
- Timothy Obiso, Kenneth Lai, Abhijnan Nath, Nikhil Krishnaswamy, and James Pustejovsky. 2025. Dynamic Epistemic Friction in Dialogue. In Proceedings of the 29th Conference on Computational Natural Language Learning, pages 323–333, Vienna, Austria. Association for Computational Linguistics.