Paper Detail

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

Mathis Immertreu, Fitim Abdullahu, Thomas Kinfe, Claus Metzner, Helmut Grabner, Patrick Krauss, Achim Schilling

arxiv Score 8.2

Published 2026-11-05 · First seen 2026-11-07

General AI

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.

Workflow Status

Review status
pending
Role
unreviewed
Read priority
soon
Vote
Not set.
Saved
no
Collections
Not filed yet.
Next action
Not filled yet.

Reading Brief

No structured notes yet. Add `summary_sections`, `why_relevant`, `claim_impact`, or `next_action` in `papers.jsonl` to enrich this view.

Why It Surfaced

No ranking explanation is available yet.

Tags

No tags.

BibTeX

@article{immertreu2026geometry,
  title = {The Geometry of Simulated Perspectives: Dissociating Representation and Behaviour in a Multimodal Language Model},
  author = {Mathis Immertreu and Fitim Abdullahu and Thomas Kinfe and Claus Metzner and Helmut Grabner and Patrick Krauss and Achim Schilling},
  year = {2026},
  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 lay},
  url = {https://arxiv.org/abs/2611.08262},
  keywords = {cs.AI, cs.CL, cs.CV},
  eprint = {2611.08262},
  archiveprefix = {arXiv},
}

Metadata

{}