模型推理时会误用群体统计偏见，导致对个体的不公平判断。
Wait, am I Being Fair? Characterizing Deductive Stereotyping and Mitigating It with Fair-GCG
- 发现模型在推理中将群体规律错误套用于个体，产生看似合理却偏见的结论。
- 提出公平注入框架，用Fair-GCG自动发现有效纠偏短语，提升多场景公平性。
- 效果可跨模型大小迁移，适用于开放生成与真实敏感任务。
尽管近期大语言模型的推理能力有所提升，但公平性问题仍存。本文识别出一种新故障模式——演绎式刻板印象：模型将群体层面的统计规律错误应用于个体案例，生成逻辑自洽却社会偏见严重的推论。我们从统计角度解释该现象，并提出一种推理时注入的纠正框架。进一步设计Fair-GCG系统，用于系统性发现有效的纠正短语。经Fair-GCG发现的注入短语，在多个公平性基准上均表现更优，具备从小模型到大模型的泛化能力，显著提升推理层级的公平性，减少开放式生成中的偏见，并成功迁移到真实世界中的公平敏感任务。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。