arXiv cs.AI· Jiawei Chen·· 14 小时前AI 评分42
研究：文本人设难让视觉语言模型像所描述的人那样“看”
Telling Is Not Seeing: Textual Personas Rarely Make Vision-Language Models Answer Like the People They Describe
AI 导读
研究对比了视觉语言模型在文本人设下的回答与低视力、色盲或听障人群的实际测量结果，发现人设从未优于仅使用人设所述事实的简单规则，还抹平了群体与个体间的真实差异。在测试的全部 14 个模型中，描述“模糊”均未改变识别表现，而实际模糊照片会像对人一样降低识别率。模型能估计模糊和错觉对人的影响，却无法在回答中体现这些效果。
正文 · 原文
Abstract:Vision-language models (VLMs) are increasingly prompted with personas, such as "You have low vision", to stand in for people in user studies. We ask whether a persona makes a model see like the person it describes. We compare persona answers with measured people with low vision, color blindness or hearing loss, and with simple rules that use only the facts the persona states. The persona never beats these rules, and it erases the real differences between groups and individuals. Describing blur leaves recognition unchanged in all 14 models we test, while blurring the photo lowers it as it does for people. Inside open models, the description changes neither the image information nor the answer probabilities. Yet the models know the effects they fail to show: they can estimate how blur and illusions affect people. Telling is not seeing: a persona makes a model say what it knows about people, not see what they see.
| Subjects: | Computer Vision and Pattern Recognition (cs.CV); Artificial Intelligence (cs.AI) |
| Cite as: | arXiv:2610.39331 [cs.CV] |
| (or arXiv:2610.39331v1 [cs.CV] for this version) | |
| https://doi.org/10.48550/arXiv.2610.39331 arXiv-issued DOI via DataCite (pending registration) |
Submission history
From: Jiawei Chen [view email]
[v1]
Thu, 29 Oct 2026 04:26:29 UTC (299 KB)
来源：arXiv cs.AI · arxiv.org