研究：文本人设提示无法让视觉语言模型像所描述人群那样看图
Telling Is Not Seeing: Textual Personas Rarely Make Vision-Language Models Answer Like the People They Describe
AI 导读
arXiv 论文（arXiv:2610.39331）测试人设提示能否让视觉语言模型像其所描述的人一样感知，覆盖 14 个模型并与低视力、色盲、听力障碍人群实测对比。结果发现人设回答从未超过仅用其陈述事实的简单规则，描述模糊不改变识别结果而真实模糊图像会降低识别，且人设抹平了群体与个体间的真实差异；模型虽能估算模糊和错觉对人的影响，但内部图像信息与回答概率均未改变。
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