Metraipolis › archive › dc_c4b60e78258a

Meaning Contracts: Local Semantic Geometry in Large Language Models — arXiv:2610.30715

Source
arXiv (en)
Original
https://arxiv.org/abs/2610.30715
License (as archived)
CC0-1.0
Archived
2026-10-25T08:34:37.346Z
SHA-256 of the archived text
ba0cbe1b802be640d4291a7ac9ebb5a5cc39fac22fb3d20038ad50d29f224643
Stable URL of this page
https://metraipolis.com/documento/dc_c4b60e78258a

How to cite

Meaning Contracts: Local Semantic Geometry in Large Language Models — arXiv:2610.30715 — arXiv (en), https://arxiv.org/abs/2610.30715 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_c4b60e78258a (Metraipolis archive dc_c4b60e78258a, sha256 ba0cbe1b802be640d4291a7ac9ebb5a5cc39fac22fb3d20038ad50d29f224643)
BibTeX
@misc{dcc4b60e78258a,
  title = {Meaning Contracts: Local Semantic Geometry in Large Language Models — arXiv:2610.30715},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2610.30715},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_c4b60e78258a; sha256 ba0cbe1b802be640d4291a7ac9ebb5a5cc39fac22fb3d20038ad50d29f224643},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.30715. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

This paper studies the local geometry of semantic meaning in large language models. Current representation analyses ask whether meanings are close in embedding space, or whether linear probes separate semantic classes, but they do not characterize the within-concept local geometry: what is invariant across realizations of a single semantic factor, what varies, and what changes when meaning is refined. This paper characterizes that geometry through two controlled probes evaluated on four architecturally diverse decoder-only LLMs (Gemma 4, Llama 3.2, Qwen 2.5, Pythia). A cross-lingual probe uses language as a perturbation to separate exact meaning matches, same-factor realizations, nearby concepts, and out-of-domain contrasts. A refinement probe separates specificity-bearing semantic narrowing from high-probability attributive elaboration and adversarial controls; both probes are validated by blind human judgments. Four findings recur across all models: under mean pooling, once dominant variance directions are removed, sentence pairs order by semantic relatedness (same factor, then same domain, then different domain) without overlap over a band of layers; semantic factors organize around an invariant core surrounded by structured realization-specific variation; refinement produces directed displacement into tighter neighborhoods, including against controls built on the same base noun; and sentence-level and token-local readouts expose complementary geometry (volume contraction at the sentence level, sharper anisotropic endpoints at token-local readout). We interpret these results as evidence that LLM semantics are organized as local anisotropic neighborhoods in which meaning contracts under refinement.

Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.AI, nuovi lavori del giorno).
Categorie arXiv: Computation and Language (cs.CL) ; Artificial Intelligence (cs.AI).
Pagina del lavoro: https://arxiv.org/abs/2610.30715 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito).
Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina.
Letto il 2026-10-25T08:31:13.183Z dalla pagina https://arxiv.org/list/cs.AI/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).