From Human Cognition to Neural Activations: Probing the Computational Primitives of Spatial Reasoning in LLMs

Dimensions overall score 3.0

GitHub Code Pulse

No public code linked for this paper yet.

• Task-relevant spatial information is encoded in intermediate layers of LLMs and can causally influence behavior.result 95%
• Spatial representations in LLMs are transient, fragmented across task families, and weakly integrated into final predictions.limitation 95%
• LLMs exhibit mechanistic degeneracy, where similar behavioral performance arises from distinct internal pathways across different languages.result 95%
• Spatial representations in LLMs are constructed during intermediate processing but are not preserved into the final layers responsible for token prediction.result 90%
• Program Execution shows the strongest and most consistent performance across languages, while Orientation Reasoning performs near chance level.result 90%
• Instruction-tuned models consistently show stronger spatial representations than base models.result 85%
• The study employs a mechanistic perspective by examining internal representations and using controlled task families for three spatial reasoning primitives: relational composition, representational transformation, and stateful spatial updating.method 95%
• Current LLMs exhibit limited and context-dependent spatial representations rather than robust, general-purpose spatial reasoning.limitation 95%

Competitive landscape

Competitor map is still being generated for this paper. Enable generation or check back soon.

Startup potential card