IMPLICIT-Bench：在中性提示下测量文本到图像模型中的隐性偏见

中文摘要 AI 辅助

文本到图像（T2I）模型通常使用基于槽的模板（如“一张[职业]的照片”）来评估偏见。此类模板仅孤立地探测显性的人口统计属性（如性别、肤色），却忽略了自然提示中出现的更广泛的隐性偏见：当与刻板印象相关的属性未被指定时，模型仍会默认生成刻板印象的输出。我们引入了IMPLICIT-Bench，一个用于在此类提示下测量T2I模型中隐性偏见的基准。其关键设计是基于结构化知识图谱（KG）构建受控的提示三元组：中性、刻板印象和反刻板印象变体，这些变体仅沿单一偏见维度不同，同时保持场景语义不变。这使得能够精确归因偏见效应，而模板基准无法实现这一点。IMPLICIT-Bench包含11个偏见类别下的5,493个提示，并通过多模型一致性、基于CLIP的验证和人工评估进行了验证。利用该基准，我们表明最先进的T2I模型在中性提示下表现出系统性偏见，这是一种现有评估大多无法发现的失败模式。随后，我们使用IMPLICIT-Bench评估去偏见方法，揭示了偏见减少与语义保真度之间的根本权衡。

英文摘要

Text-to-image (T2I) models are typically evaluated for bias using slot-based templates such as ``a photo of a [profession]''. Such templates probe only \emph{explicit} demographic attributes (e.g., gender, skin tone) in isolation. They overlook a broader \emph{implicit} bias that arises in natural prompts: when stereotype-relevant attributes are left unspecified, models still default to stereotypical outputs. We introduce IMPLICIT-Bench, a benchmark for measuring implicit bias in T2I models under such prompts. The key design is a structured-knowledge-graph (KG) construction of controlled prompt triplets: neutral, stereotype, and anti-stereotype variants that differ only along a single bias dimension while preserving scene semantics. This enables precise attribution of bias effects that template benchmarks cannot achieve. IMPLICIT-Bench comprises 5,493 prompts across 11 bias categories, validated through multi-model agreement, CLIP-based verification, and human evaluation. Using this benchmark, we show that state-of-the-art T2I models exhibit systematic bias under neutral prompts, a failure mode largely invisible to existing evaluations. We then use IMPLICIT-Bench to evaluate debiasing methods, uncovering a fundamental trade-off between bias reduction and semantic fidelity.

发表机构

• The University of Melbourne（墨尔本大学）

机构由 AI 辅助整理，请以论文原文为准。