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

Paper recorded by Signals 4 on 2026-08-30 in cs.AI. Abstract reproduced from arXiv; link to the original below.

Published 2026-08-30 on arXiv · recorded by Signals 4 on 2026-09-01

Category: cs.AI · 人工智能 · first seen 2026-09-01

Abstract

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 o

Read on arXiv →