Metraipolis › archive › dc_bf177cc71696

The Geometry of Simulated Perspectives: Dissociating Representation and Behaviour in a Multimodal Language Model — arXiv:2611.08262

Source
arXiv (en)
Original
https://arxiv.org/abs/2611.08262
License (as archived)
CC0-1.0
Archived
2026-11-06T14:41:56.188Z
SHA-256 of the archived text
3d4cd0d4b062f29674a20308cb8563d9f19d95a5b3f11b6cd74667c7a8f345d0
Stable URL of this page
https://metraipolis.com/documento/dc_bf177cc71696

How to cite

The Geometry of Simulated Perspectives: Dissociating Representation and Behaviour in a Multimodal Language Model — arXiv:2611.08262 — arXiv (en), https://arxiv.org/abs/2611.08262 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_bf177cc71696 (Metraipolis archive dc_bf177cc71696, sha256 3d4cd0d4b062f29674a20308cb8563d9f19d95a5b3f11b6cd74667c7a8f345d0)
BibTeX
@misc{dcbf177cc71696,
  title = {The Geometry of Simulated Perspectives: Dissociating Representation and Behaviour in a Multimodal Language Model — arXiv:2611.08262},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2611.08262},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_bf177cc71696; sha256 3d4cd0d4b062f29674a20308cb8563d9f19d95a5b3f11b6cd74667c7a8f345d0},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2611.08262. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

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.

Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.AI, nuovi lavori del giorno).
Categorie arXiv: Artificial Intelligence (cs.AI) ; Computation and Language (cs.CL); Computer Vision and Pattern Recognition (cs.CV).
Pagina del lavoro: https://arxiv.org/abs/2611.08262 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito).
Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina.
Letto il 2026-11-06T14:18:42.654Z dalla pagina https://arxiv.org/list/cs.AI/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).