{"slug": "wait-am-i-being-fair-characterizing-deductive-stereotyping-and-mitigating-it-gcg", "title": "Wait, am I Being Fair? Characterizing Deductive Stereotyping and Mitigating It with Fair-GCG", "summary": "Researchers at arXiv identify a failure mode in large language models called deductive stereotyping, where models apply population-level statistics to individuals, producing biased inferences. They propose Fair-GCG, a reasoning-time injection framework that discovers phrases to steer models toward fairness-aware reasoning, improving performance across fairness benchmarks and reducing bias in open-ended generation.", "body_md": "arXiv:2606.30989v1 Announce Type: new\nAbstract: 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 propose a reasoning-time injection framework. We further introduce Fair-GCG to systematically discover effective injection phrases. Injection phrases discovered by Fair-GCG improve performance across multiple fairness benchmarks, generalize from smaller to larger LLMs, improves reasoning-level fairness, reduces bias in open-ended generation, and transfer to real-world fairness-sensitive tasks.", "url": "https://wpnews.pro/news/wait-am-i-being-fair-characterizing-deductive-stereotyping-and-mitigating-it-gcg", "canonical_source": "https://arxiv.org/abs/2606.30989", "published_at": "2026-07-01 04:00:00+00:00", "updated_at": "2026-07-01 04:22:52.210463+00:00", "lang": "en", "topics": ["large-language-models", "ai-ethics", "ai-safety", "ai-research"], "entities": ["arXiv"], "alternates": {"html": "https://wpnews.pro/news/wait-am-i-being-fair-characterizing-deductive-stereotyping-and-mitigating-it-gcg", "markdown": "https://wpnews.pro/news/wait-am-i-being-fair-characterizing-deductive-stereotyping-and-mitigating-it-gcg.md", "text": "https://wpnews.pro/news/wait-am-i-being-fair-characterizing-deductive-stereotyping-and-mitigating-it-gcg.txt", "jsonld": "https://wpnews.pro/news/wait-am-i-being-fair-characterizing-deductive-stereotyping-and-mitigating-it-gcg.jsonld"}}