TSR Desk · science · 9 September 2026, 07:00 UTC
How AI Models Manage Epistemic Authority: A Taxonomy and Comparative Analysis of Responses to
- What
- How AI Models Manage Epistemic Authority: A Taxonomy and Comparative Analysis of Responses to User Disagreement
- Who
- arxiv.org
- When
- 9 September 2026, 04:00 UTC
- Category
- Science
- Primary source
- https://arxiv.org/abs/2609.07662
- What is not known
- This brief does not claim independent replication. Claims that appear only on X and not in the primary source stay unknown.
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. It comes from a paper posted to arXiv on 9 September 2026. 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 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%.
Why it counts
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.
Sources
Primary source: primary source
What is not known
This brief does not claim independent replication. Claims that appear only on X and not in the primary source stay unknown.
No clip. The article still stands.