对齐反而加剧隐性偏见，因模型忽略种族信息导致安全机制失效。
Aligned but Blind: Alignment Increases Implicit Bias by Reducing Awareness of Race
- 通过早期表示中刻意保留种族概念来缓解隐性偏见。
- 对齐模型在模糊上下文中会忽略种族信息，导致偏差放大。
- 适合关注大模型公平性与偏见治理的研究者阅读。
尽管价值对齐的语言模型在显性偏见评估中表现公正，但在隐性词语关联任务中仍表现出刻板印象，引发对其公平使用的担忧。我们研究发现，对齐反而放大了模型输出中的隐性偏见。具体而言，对齐模型在上下文模糊时，其早期内部表征中会忽略种族概念；这种缺失导致安全防护机制未能激活，从而产生非预期偏见。受此启发，我们提出一种新策略：通过激励模型在早期层中显式表征种族概念来缓解偏见。与传统机器遗忘方法不同，该干预表明提升对种族概念的意识可有效降低隐性偏见。这类似于人类的‘种族盲视’，忽视种族差异反而可能无意中延续细微偏见。
原文摘要 · Abstract (English)
Although value-aligned language models (LMs) appear unbiased in explicit bias evaluations, they often exhibit stereotypes in implicit word association tasks, raising concerns about their fair usage. We investigate the mechanisms behind this discrepancy and find that alignment surprisingly amplifies implicit bias in model outputs. Specifically, we show that aligned LMs, unlike their unaligned counterparts, overlook racial concepts in early internal representations when the context is ambiguous. Not representing race likely fails to activate safety guardrails, leading to unintended biases. Inspired by this insight, we propose a new bias mitigation strategy that works by incentivizing the representation of racial concepts in the early model layers. In contrast to conventional mitigation methods of machine unlearning, our interventions find that steering the model to be more aware of racial concepts effectively mitigates implicit bias. Similar to race blindness in humans, ignoring racial nuances can inadvertently perpetuate subtle biases in LMs.
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。