Metraipolis › archive › dc_ea24fd8596b7
Answering clinicians' questions over trial evidence tables with verifiable, feedback-driven language models — arXiv:2610.02576
- Source
- arXiv
- Original
- https://arxiv.org/abs/2610.02576
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-05T22:49:03.832Z
- SHA-256 of the archived text
452544f8d1d32aba6c9dcc8444a844208e3de679666af4e6844ec1d19d5a4beb- Stable URL of this page
https://metraipolis.com/documento/dc_ea24fd8596b7
How to cite
Answering clinicians' questions over trial evidence tables with verifiable, feedback-driven language models — arXiv:2610.02576 — arXiv, https://arxiv.org/abs/2610.02576 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_ea24fd8596b7 (Metraipolis archive dc_ea24fd8596b7, sha256 452544f8d1d32aba6c9dcc8444a844208e3de679666af4e6844ec1d19d5a4beb)
BibTeX
@misc{dcea24fd8596b7,
title = {Answering clinicians' questions over trial evidence tables with verifiable, feedback-driven language models — arXiv:2610.02576},
howpublished = {arXiv},
url = {https://arxiv.org/abs/2610.02576},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_ea24fd8596b7; sha256 452544f8d1d32aba6c9dcc8444a844208e3de679666af4e6844ec1d19d5a4beb},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv, https://arxiv.org/abs/2610.02576. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Systematic reviews condense clinical trials into evidence tables, yet clinicians can interrogate these tables only through database queries, and many questions concern attributes that the table does not record, such as a drug's target class or a harmonised endpoint. Here we introduce FD-SCoPE, a language-model framework that answers both kinds of question, exposes the query, the selected trials and the derivation rule behind every answer, and learns from expert corrections. On an oncology evidence table of 159 immune checkpoint inhibitor trial records, FD-SCoPE completed all 140 clinician-style tasks (alternatives, 90.7-97.9%). For questions needing derived attributes it retrieved 99.3% of relevant trial records at a positive predictive value of 89.8% and outperformed four alternative approaches (derived-value F1 77.7% versus 64.8-73.4%). Corrections on 299 questions, simulated from reference answers, raised F1 on 1,201 unseen questions from 77.9% to 84.9%. Language models coupled with executable queries, verified programs and expert feedback can give clinicians auditable access to trial evidence. 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/2610.02576 — 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 2026-10-05T22:45:55.602Z dalla pagina https://arxiv.org/list/cs.AI/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).