{
  "id": 426,
  "url": "https://arxiv.org/abs/2606.30989v1",
  "title": "Wait, am I Being Fair? Characterizing Deductive Stereotyping and Mitigating It with Fair-GCG",
  "summary": "Warning: This paper contains several toxic and offensive statements. While reasoning generally improves fairness in recent large language models (LLMs), failures persist. In this work, we identify a failure mode, deductive stereotyping, in which models apply population-level statistical regularities to individual cases, producing logically coherent yet socially biased inferences. We provide a statistical interpretation of this phenomenon. To steer models toward fairness-aware reasoning, we propo",
  "authors": "Naihao Deng, Yilun Zhu, Joan Nwatu, Clayton Scott, Rada Mihalcea",
  "category": "research",
  "topics": "bias-fairness",
  "orgs": null,
  "regions": null,
  "published_at": "2026-06-30T00:00:42.000Z",
  "fetched_at": "2026-07-14T14:14:32.646Z",
  "source_slug": "arxiv-ethics",
  "source_name": "arXiv",
  "source_homepage": "https://arxiv.org",
  "ethics_ai_record_url": "https://ethics.ai/record/426",
  "original_url": "https://arxiv.org/abs/2606.30989v1",
  "evidence_status": "source-only",
  "attribution": "via ethics.ai"
}