{
  "id": 38,
  "url": "https://arxiv.org/abs/2607.10578v1",
  "title": "Laguerre Geometry for Interpreting Large Language Models",
  "summary": "Existing hypotheses represent a concept in an LLM as a single point, a linear direction, or a Gaussian cluster, yet it remains unclear how and why such structures emerge. Here, we show that concept geometry can be precisely characterized via Laguerre Geometry, in which a concept is defined as a region--a Laguerre-Voronoi cell or a union of cells--allowing us to strictly define, measure, and separate concepts. Building on this formulation, we show that finer-grained concept structures, such as in",
  "authors": "Chunwei Ma, Russell Wolfinger",
  "category": "research",
  "topics": null,
  "orgs": null,
  "regions": null,
  "published_at": "2026-07-12T05:28:48.000Z",
  "fetched_at": "2026-07-14T14:14:15.664Z",
  "source_slug": "arxiv-ethics",
  "source_name": "arXiv",
  "source_homepage": "https://arxiv.org",
  "ethics_ai_record_url": "https://ethics.ai/record/38",
  "original_url": "https://arxiv.org/abs/2607.10578v1",
  "evidence_status": "source-only",
  "attribution": "via ethics.ai"
}