Metraipolis › archive › dc_90ceaff60f42
Propagating construction-time knowledge quality into medical question answering: A framework grounded in clinical guidelines — arXiv:2608.28360
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2608.28360
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-17T10:47:36.302Z
- SHA-256 of the archived text
cfdb928893886e41b39907f3466f056552a9c9acddbb6e4aeb07d4ea0d08b34a- Stable URL of this page
https://metraipolis.com/documento/dc_90ceaff60f42
How to cite
Propagating construction-time knowledge quality into medical question answering: A framework grounded in clinical guidelines — arXiv:2608.28360 — arXiv (en), https://arxiv.org/abs/2608.28360 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_90ceaff60f42 (Metraipolis archive dc_90ceaff60f42, sha256 cfdb928893886e41b39907f3466f056552a9c9acddbb6e4aeb07d4ea0d08b34a)
BibTeX
@misc{dc90ceaff60f42,
title = {Propagating construction-time knowledge quality into medical question answering: A framework grounded in clinical guidelines — arXiv:2608.28360},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2608.28360},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_90ceaff60f42; sha256 cfdb928893886e41b39907f3466f056552a9c9acddbb6e4aeb07d4ea0d08b34a},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2608.28360. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Large language models have facilitated knowledge graph (KG) construction from clinical guidelines, but extracted triples vary in structural validity and evidential support. Meanwhile, graph-augmented question answering (QA) systems typically optimize query relevance during retrieval, with limited reuse of quality information produced during KG construction. This creates a disconnect between construction-time quality control and inference-time evidence use. We investigate whether construction-time triple quality can serve as a persistent signal for downstream evidence selection and presentation. We propose a quality-aware framework that models structural conformance (SchemaConf) and evidential support (EvidScore) as complementary dimensions and fuses them into a per-triple quality signal, Q(t). Rather than using quality solely for filtering, the framework retains Q(t) and derived quality tiers as graph attributes and propagates them into quality-weighted subgraph retrieval and tier-conditioned evidence prompting, while preserving passage-level provenance. Experiments on Chinese diabetes clinical guidelines show that the utility of the quality signal is distribution dependent. Under cross-version and cross-model shift, the fused Q(t) provides stronger triple-quality discrimination than either component alone (AUC 0.748 vs. 0.703 for EvidScore and 0.645 for SchemaConf). In guideline-grounded QA, propagating construction-time quality reduces required-knowledge omission from 16.3% to 5.3% and conflicting outputs from 16.3% to 2.7%, with an evidence-grounded precision of 81.6% and near-zero invalid citations. Blinded clinician ratings favor the full framework over no retrieval (4.68 vs. 4.21 on a five-point scale) and approach the oracle condition (4.80), while cross-generator experiments show consistent trends. Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-08-31 in cs.AI). Categorie arXiv: Artificial Intelligence (cs.AI). Pagina del lavoro: https://arxiv.org/abs/2608.28360 — 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 2026-10-17T10:33:42.420Z dalla pagina https://arxiv.org/catchup/cs.AI/2026-08-31?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).