RESEARCHMonitorNEXT 12 MONTHS
Authority Bias in Language Models: Source Deference and User Agreement Are Not Interchangeable
arXiv cs.CL — Computation and Language
Factual evidence
What the source reports
Research reveals LLMs defer more readily to incorrect answers attributed to authoritative sources than to user assertions in RAG workflows.
Inspect the evidence
- Inclusion basis
- Enterprise AI
- Publisher and source type
- arXiv cs.CL — Computation and Language · RESEARCH
- Published by source
- 30 September 2026
- Collected by OneBench
- 1 Oct 2026, 03:01 UK
Stored source excerpt
arXiv:2609.37616v1 Announce Type: cross Abstract: Language models tend to agree with whatever a user asserts, and post-training increasingly targets this sycophancy so that models evaluate…
Short excerpt from the collected text, not the full source. Use the source link to read it in context.
The factual summary is a OneBench synthesis, not a quotation or independent verification. Collection time is not publication time. Open the source for its full context; related reporting can share the same underlying announcement.