Vision-Language Models Suppress Female Representations Under Ambiguous Input 事件

Vision-Language Models Suppress Female Representations Under Ambiguous Input arXiv:2605.31556v1 Announce Type: new Abstract: Alignment teaches vision-language models (VLMs) to avoid expressing demographic biases, and when gender is clearly visible they largely succeed. Far less is known about ambiguous inputs (a worker in full gear, a figure seen from behind) cases common in practice yet rarely studied. We find that minimal prompting pressure exposes occupation-gender defaults when prompting am