论文揭示了AI图像生成系统对非标准方言用户的系统性歧视，可通过重新训练减轻。
研究评估了23,080个跨五种英语方言的提示对，发现文本到图像安全护栏存在方言惩罚现象。NSFW-T过滤器过度标记良性方言提示，LatentGuard过度标记有毒提示，偏差差距高达+28.29个百分点。OpenAI内容审核API则未能检测到这些提示。像素级生成器基本不受方言影响，偏见主要出现在文本处理环节。
Not Safe for All: Auditing the Dialect Penalty in Text-to-Image Safety Pipelines
Text-to-image (T2I) safety guardrails fail to generalize equitably to non-standard dialects. Evaluating 23,080 paired prompts across five English dialects, we formalize this failure as the dialect penalty, where filters trigger based on linguistic surface features rather than semantic intent. Text-level filters fail in opposing directions: NSFW-T over-flags benign dialect prompts and LatentGuard over-flags toxic ones (bias gaps up to +28.29 pp), while the OpenAI Moderation API under-detects them. A controlled typo ablation confirms this penalty originates from flagging dialectal features, not generic out-of-distribution sensitivity. The pixel-level generator is largely dialect-agnostic; the penalty enters at text processing and cascades unevenly to post-hoc guardrails. We show this bias tracks training data imbalance and is mitigable via group-balanced retraining, with an ablation attributing the gain to balanced exposure rather than to the worst-group objective of GroupDRO (group distributionally robust optimization). Current pipelines systematically fail dialect speakers, an equity failure masked by mean accuracy benchmarks. Our official code and dataset are publicly available at https://github.com/minguinho26/dialect-penalty-t2i. Content Warning: This paper contains offensive, toxic, or disturbing text prompts and generated images.