RESEARCHInvestigateNOW
Same Facts, Different Remedy: Linguistic Profiling and Arbitrariness in LLM and System One Decisions
arXiv cs.CL — Computation and Language
Factual evidence
What the source reports
Audit of GPT-4o-mini and GPT-5-mini shows LLMs alter financial complaint remedy decisions based on consumer writing style.
Inspect the evidence
- Inclusion basis
- Enterprise AI
- Publisher and source type
- arXiv cs.CL — Computation and Language · RESEARCH
- Published by source
- 9 November 2026
- Collected by OneBench
- 10 Nov 2026, 02:01 UK
Stored source excerpt
arXiv:2611.08995v1 Announce Type: cross Abstract: Large language models are increasingly used to resolve consumer complaints, and the way complainants write varies with age, education and…
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.