Metraipolis › archive › dc_be2a58f6acba
RareDx: Controlled Knowledge Integration and Graph-Grounded Policy Optimization for Rare-Disease Diagnosis — arXiv:2609.35549
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2609.35549
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-07T20:58:53.019Z
- SHA-256 of the archived text
31b2731da18acc583b330ffcf11a6ee6f2529da71e949999a0e7cc95fb017e4b- Stable URL of this page
https://metraipolis.com/documento/dc_be2a58f6acba
How to cite
RareDx: Controlled Knowledge Integration and Graph-Grounded Policy Optimization for Rare-Disease Diagnosis — arXiv:2609.35549 — arXiv (en), https://arxiv.org/abs/2609.35549 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_be2a58f6acba (Metraipolis archive dc_be2a58f6acba, sha256 31b2731da18acc583b330ffcf11a6ee6f2529da71e949999a0e7cc95fb017e4b)
BibTeX
@misc{dcbe2a58f6acba,
title = {RareDx: Controlled Knowledge Integration and Graph-Grounded Policy Optimization for Rare-Disease Diagnosis — arXiv:2609.35549},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2609.35549},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_be2a58f6acba; sha256 31b2731da18acc583b330ffcf11a6ee6f2529da71e949999a0e7cc95fb017e4b},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.35549. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Rare-disease diagnosis is a long-tail reasoning problem: phenotypes are incomplete, individual disorders are sparsely documented, and relevant evidence is distributed across ontologies, gene annotations, and biomedical text. Language models consequently favor common conditions, miss rare candidates, or produce plausible but invalid names. We introduce RareDx, which couples controlled evidence use with knowledge-graph-grounded policy optimization. RareDx-Harness normalizes heterogeneous records into one ranked-diagnosis task and compares direct inference, static retrieval, adaptive tools, and structured phenotype-gene-disease reasoning over a shared knowledge layer. The training pipeline combines Top-10 post-training with RareDx-KGPO, our knowledge-graph-grounded policy optimization method. Its reward projects predictions into a canonical disease graph and integrates curated graded relevance, ontology proximity, biomedical similarity, and phenotype consistency. Vocabulary and output-budget constraints prevent dense partial credit from rewarding fabricated or overlong differentials. Across eight benchmarks, the complete RareDx system centered on Qwen3.5-9B reaches 38.34 macro Hit@10, 1.60 points above GPT-5.5 under the archived protocol; a disjoint validation-selection audit retains a 6.80-point routing gain over Direct on held-out cases. The 27B system reaches 23.53/36.56/40.76 at Hit@1/5/10. Controlled ablations show that retrieval is not uniformly helpful and that controlled routing is central to the gain. These results indicate that structured medical knowledge can turn a compact model into a competitive diagnostic ranker across heterogeneous long-tail settings in clinical practice. Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-29 in cs.AI). Categorie arXiv: Artificial Intelligence (cs.AI). Pagina del lavoro: https://arxiv.org/abs/2609.35549 — 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 2026-10-07T20:29:01.881Z dalla pagina https://arxiv.org/catchup/cs.AI/2026-09-29?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).