RESEARCHMonitorNEXT 12 MONTHS
Persuaded, Not Informed: Incentive-Misaligned Witnesses Defeat In-Context Grounding
arXiv cs.CL — Computation and Language
Factual evidence
What the source reports
Research shows LLM agents fail in-context grounding by treating biased human assertions in CRM records as factual evidence.
Inspect the evidence
- Inclusion basis
- Enterprise AI
- Publisher and source type
- arXiv cs.CL — Computation and Language · RESEARCH
- Published by source
- 25 September 2026
- Collected by OneBench
- 26 Sept 2026, 03:01 UK
Stored source excerpt
arXiv:2609.28854v1 Announce Type: new Abstract: Language-model agents increasingly answer questions over customer-relationship management (CRM) records, such as whether to qualify a sales lead. We identify…
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.