arXiv cs.AI· Mathis Immertreu, Fitim Abdullahu, Thomas Kinfe, Claus Metzner, Helmut Grabner, Patrick Krauss, Achim Schilling·· 11 小时前AI 评分29
Qwen3-VL-8B-Instruct 中模拟视角的几何：表征与行为的分离
The Geometry of Simulated Perspectives: Dissociating Representation and Behaviour in a Multimodal Language Model
AI 导读
研究者在 Qwen3-VL-8B-Instruct 上用 100 张图像、53 种提示条件考察人格化视角下的视觉趣味性判断，发现表征几何随处理深度系统性重组：浅层主要编码图像身份，人格相关结构在深层才出现。提示词框架对内部表征的重塑强于人格身份本身，而人格内容对行为评分影响更大，二者出现分离；不改变回答的最小身份陈述也能改变表征，说明表征距离未必对应行为相关性。
正文 · 原文
Abstract:Multimodal language models can simulate different observers, yet it remains unclear how assigned perspectives reshape their internal representations and whether these changes govern their judgements. Here, we investigate the representational geometry of persona-conditioned visual interestingness in Qwen3-VL-8B-Instruct. Across 100 images and 53 prompting conditions, we systematically vary persona content and the linguistic framing used to introduce it, while recording behavioural ratings and layer-wise hidden states. We observe a systematic reorganisation of representational geometry across processing depth: early layers primarily encode image identity, whereas persona-specific structures emerge in later layers. Strikingly, prompt framing reshapes internal representations more strongly than persona identity, whereas persona content has a greater impact on behavioural judgements. This dissociation is further illustrated by minimal identity statements that alter representations even without changing responses. These findings demonstrate that representational distance does not necessarily reflect behavioural relevance. More broadly, they reveal how simulated perspectives emerge as distinct structures within the representational space of artificial cognitive systems, highlighting a fundamental distinction between the geometry of internal representations and their functional consequences.
| Comments: | 30 pages, 10 figures, 2 tables. Code: this https URL data: this https URL |
| Subjects: | Artificial Intelligence (cs.AI); Computation and Language (cs.CL); Computer Vision and Pattern Recognition (cs.CV) |
| Cite as: | arXiv:2611.08262 [cs.AI] |
| (or arXiv:2611.08262v1 [cs.AI] for this version) | |
| https://doi.org/10.48550/arXiv.2611.08262 arXiv-issued DOI via DataCite (pending registration) |
Submission history
From: Mathis Immertreu [view email]
[v1]
Thu, 5 Nov 2026 16:36:49 UTC (1,135 KB)
来源：arXiv cs.AI · arxiv.org