Metraipolis › archive › dc_7806532b60eb

Surgical Alignment in Knowledge Graph Training for Clinical Diagnosis with Large Language Models — arXiv:2608.26587

Source: arXiv (en)
Original: https://arxiv.org/abs/2608.26587
License (as archived): CC0-1.0
Archived: 2026-10-17T15:19:37.320Z
SHA-256 of the archived text: 8a3c204d58e7f10c187053df1341f2625764326ba0593bb1db4d67b646c011c5
Stable URL of this page: https://metraipolis.com/documento/dc_7806532b60eb

How to cite

Surgical Alignment in Knowledge Graph Training for Clinical Diagnosis with Large Language Models — arXiv:2608.26587 — arXiv (en), https://arxiv.org/abs/2608.26587 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_7806532b60eb (Metraipolis archive dc_7806532b60eb, sha256 8a3c204d58e7f10c187053df1341f2625764326ba0593bb1db4d67b646c011c5)

BibTeX

@misc{dc7806532b60eb,
  title = {Surgical Alignment in Knowledge Graph Training for Clinical Diagnosis with Large Language Models — arXiv:2608.26587},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2608.26587},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_7806532b60eb; sha256 8a3c204d58e7f10c187053df1341f2625764326ba0593bb1db4d67b646c011c5},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2608.26587. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Biomedical knowledge graphs (KGs) offer structured medical knowledge that can ground large language model (LLM) reasoning in clinical diagnosis application, yet how KG signal should be integrated into LLMs remains an open question. We present a systematic study spanning five KG task formulations, three training paradigms, two KGs, and three base LLMs. At the task level, all paradigms improve over the non-finetuned baseline, but methods with comparable in-domain accuracy show substantially different knowledge transfer behavior. We introduce Gradient Intervention Density (GID) and Gradient Distortion (GD) to measure how broadly an optimizer modifies the pretrained model. GID and GD together reveal a clear divide: KG-judgment training under KL regularization produces sparse, localized updates (a regime we term as surgical alignment), while task-specific SFT produces dense ones. A controlled ablation shows that the objective and KL contribute to sparsity independently, and the paradigms that produce sparse updates also improve reasoning quality, even when their in-domain accuracy is lower than task-specific SFT. Assessing KG-LLM integration thus requires complementing accuracy with optimization-geometry diagnostics. Our implementation can be found at this https URL .

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-08-28 in cs.CL).
Categorie arXiv: Computation and Language (cs.CL).
Pagina del lavoro: https://arxiv.org/abs/2608.26587 — 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 2026-10-17T15:15:18.061Z dalla pagina https://arxiv.org/catchup/cs.CL/2026-08-28?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).