ResearchTrend.AI
  • Papers
  • Communities
  • Events
  • Blog
  • Pricing
Papers
Communities
Social Events
Terms and Conditions
Pricing
Parameter LabParameter LabTwitterGitHubLinkedInBlueskyYoutube

© 2025 ResearchTrend.AI, All rights reserved.

  1. Home
  2. Papers
  3. 2506.02996
55
0

Linear Spatial World Models Emerge in Large Language Models

3 June 2025
Matthieu Tehenan
Christian Moya
Tenghai Long
Guang Lin
    LRM
ArXiv (abs)PDFHTML
Main:8 Pages
15 Figures
7 Tables
Appendix:13 Pages
Abstract

Large language models (LLMs) have demonstrated emergent abilities across diverse tasks, raising the question of whether they acquire internal world models. In this work, we investigate whether LLMs implicitly encode linear spatial world models, which we define as linear representations of physical space and object configurations. We introduce a formal framework for spatial world models and assess whether such structure emerges in contextual embeddings. Using a synthetic dataset of object positions, we train probes to decode object positions and evaluate geometric consistency of the underlying space. We further conduct causal interventions to test whether these spatial representations are functionally used by the model. Our results provide empirical evidence that LLMs encode linear spatial world models.

View on arXiv
@article{tehenan2025_2506.02996,
  title={ Linear Spatial World Models Emerge in Large Language Models },
  author={ Matthieu Tehenan and Christian Bolivar Moya and Tenghai Long and Guang Lin },
  journal={arXiv preprint arXiv:2506.02996},
  year={ 2025 }
}
Comments on this paper