SOURCE-LINKED INTELLIGENCE

Not Safe for All: Auditing the Dialect Penalty in Text-to-Image Safety Pipelines

arXiv · AI, language, vision and robotics · article · Aug 30, 2026 · UTC

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

Read original source ↗ Open in workspace

recordType

paper

region

Global