PaperScope
LIVE · 2026-09-09 05:40 UTC

How AI Models Manage Epistemic Authority: A Taxonomy and Comparative Analysis of Responses to User Disagreement

Riyadh Alnasser, Yusuf Mücahit Çetinkaya, Sumin Zhao, Tuğrulcan Elmas

Latestcs.CLcs.LGcs.AIcs.CV
arXiv ID
2609.07662 v1
Category
Submitted
2026-09-07

Abstract

Large language models are increasingly used as sources of advice and information, including in high-stakes settings, yet little is known about how they respond to user disagreement. We study how a model manages its epistemic authority, referring here to its claim to knowledge, competence, or the right to advise, once a user challenges its answer. Building on Conversation Analysis, we introduce a taxonomy of six challenge types and a four-layer framework for analysing each response: whether the original claim is maintained or changed, where authority is located, how the disagreement is socially managed, and what kind of evidential support is offered. We construct a new dataset of 2,310 controlled challenge scenarios and 32,340 corresponding responses from 14 models, and analyse them using our framework with an LLM-as-judge pipeline, providing a vocabulary which future evaluation and benchmark design can build on. We find that models show conflicting behaviour: they validate users in 85% of responses but maintain their original claim in 65%. They explicitly apologise in 33% of responses, yet 59% of those apologies accompany maintenance of the original claim. They transfer authority most often in advice tasks, doing so in 28% of responses and reaching 57% in health advice and 49% in legal advice, compared with 6% in fact and 3% in explanation tasks. Abandonment of the original claim ranges from 0.8% for GPT-5.2 to 40% for DeepSeek 7B, while complete replacement of the original claim is rare overall at 1.5%.

Comment: Accepted to EMNLP 2026

arXiv abs page · PDF · same-day batch