The Geometry of Knowledge Accessibility in Large Language Models

arXiv:2610.03052v1 Announce Type: new Abstract: Large language models (LLMs) contain broad knowledge, but they cannot access all of it reliably. We study this problem through knowledge accessibility, which describes whether the knowledge needed for a query can be recalled from the model. We find that knowledge accessibility has a simple geometric structure in the model's representation of the query alone, before any generation. More accessible queries are closer to a center in the representation space, while less accessible queries are farther away. This geometry reveals a knowledge boundary that separates more accessible queries from less accessible ones. Accessibility consistently decreases with distance from the center, and this distance-based ordering transfers across datasets even when the centers differ. Controlled experiments further show that the centered geometry is more closely related to knowledge accessibility than to reasoning difficulty. The geometry also reveals when different interventions are useful. Query rewriting helps more for accessible queries, chain-of-thought reasoning helps more near the boundary, and retrieval gives larger gains beyond the boundary. These findings not only provide a new geometric view of how knowledge is organized in language models, but also suggest a useful pre-generation signal for adaptive inference.

Related

• MegaRAG: Multimodal Knowledge Graph-Based Retrieval Augmented Generation
• Guaranteeing Knowledge Integration with Joint Decoding for Retrieval-Augmented Generation
• Semantic Abstraction for Natural Language Inference: a Methodological Framework for Discovering and Compensating Semantic Knowledge and Reasoning Gaps in Large Language Models
• Search-on-Graph: Iterative Informed Navigation for Large Language Model Reasoning on Knowledge Graphs

Source: arXiv cs.CL | 2026-10-05