Metraipolis › archive › dc_b092a8cfadea

Looking Inside LLMs: Small-World Connectivity as a Signature of Reasoning Performance — arXiv:2610.12304

Source
arXiv (en)
Original
https://arxiv.org/abs/2610.12304
License (as archived)
CC0-1.0
Archived
2026-10-09T05:50:38.595Z
SHA-256 of the archived text
58e6002fbab2fe9e8674cd713d0c8c42c02daff83aa39d5741cc6eb860912db4
Stable URL of this page
https://metraipolis.com/documento/dc_b092a8cfadea

How to cite

Looking Inside LLMs: Small-World Connectivity as a Signature of Reasoning Performance — arXiv:2610.12304 — arXiv (en), https://arxiv.org/abs/2610.12304 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_b092a8cfadea (Metraipolis archive dc_b092a8cfadea, sha256 58e6002fbab2fe9e8674cd713d0c8c42c02daff83aa39d5741cc6eb860912db4)
BibTeX
@misc{dcb092a8cfadea,
  title = {Looking Inside LLMs: Small-World Connectivity as a Signature of Reasoning Performance — arXiv:2610.12304},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2610.12304},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_b092a8cfadea; sha256 58e6002fbab2fe9e8674cd713d0c8c42c02daff83aa39d5741cc6eb860912db4},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.12304. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Understanding large language model (LLM) reasoning requires looking beyond behavioral performance to examine how reasoning ability is reflected in internal organization. Inspired by neuroscience findings linking higher intelligence to stronger small-world organization in functional brain networks, we investigate small-world connectivity as a structural signature of LLM reasoning. We construct functional graphs from attention-head activation similarities and find that a higher small-world index (SWI), capturing local clustering and short global paths, consistently correlates with better fluid reasoning performance across models and training checkpoints. Since local clustering is central to small-world organization, we further examine how heads important for model performance connect within and across communities. We find that these heads tend to have a larger share of connection weight within their own communities (high core scores) and a more concentrated weight distribution across communities (low bridge scores). These observations motivate the hypothesis that high core and low bridge scores serve as structural indicators of head importance for reasoning capability. We validate this hypothesis through pruning, introducing Small-World Allocation (SWA), a hierarchical sparsity allocation method guided by these scores. Across six LLMs, SWA better preserves small-world organization and model performance than competing allocation strategies, reducing WikiText perplexity by up to 20%. Together, these findings identify small-world functional connectivity as a measurable signature of LLM reasoning performance, offering a structural perspective that complements behavioral evaluation.

Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.AI, nuovi lavori del giorno).
Categorie arXiv: Artificial Intelligence (cs.AI).
Pagina del lavoro: https://arxiv.org/abs/2610.12304 — 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 2026-10-09T05:47:01.098Z dalla pagina https://arxiv.org/list/cs.AI/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).