Metraipolis › archive › dc_a7eba15bfa4f
Large language models improve physician accuracy but lead to false reliance — arXiv:2608.00817
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2608.00817
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-19T09:04:10.305Z
- SHA-256 of the archived text
83ecb9801a215308c409c07a7bc2360916e7ef1b73ac1a14fb0e3df50f21d6c5- Stable URL of this page
https://metraipolis.com/documento/dc_a7eba15bfa4f
How to cite
Large language models improve physician accuracy but lead to false reliance — arXiv:2608.00817 — arXiv (en), https://arxiv.org/abs/2608.00817 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_a7eba15bfa4f (Metraipolis archive dc_a7eba15bfa4f, sha256 83ecb9801a215308c409c07a7bc2360916e7ef1b73ac1a14fb0e3df50f21d6c5)
BibTeX
@misc{dca7eba15bfa4f,
title = {Large language models improve physician accuracy but lead to false reliance — arXiv:2608.00817},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2608.00817},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_a7eba15bfa4f; sha256 83ecb9801a215308c409c07a7bc2360916e7ef1b73ac1a14fb0e3df50f21d6c5},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2608.00817. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Retrieval-augmented large language models (LLMs) promise source-linked clinical support, but their value depends on whether displayed evidence guides rather than distorts physician reliance. We developed CORA, an agentic retrieval-augmented LLM, to investigate how source-linked assistance affects physician decision-making. CORA maintained benchmark performance and achieved larger gains on cases published after the models' training-data cutoffs. In a study of 46 physicians, accuracy increased from 70.8% unaided to 82.6% with CORA. Supporting citations predicted correct answers (87.7% vs 65.5%), but citations created an important asymmetry: perceived support increased adoption of correct advice from 34% to 76.9% but when an incorrect LLM answer appeared citation-supported, physician resistance to it fell from 92% to 34.8%. These findings show that source-linked LLM assistance can improve physician accuracy while introducing a grounding-dependent safety risk. Tema degli esploratori: statistica e scienza dei dati (retro-catalogo arXiv: annunci del 2026-08-11 in stat.AP). Categorie arXiv: Artificial Intelligence (cs.AI) ; Human-Computer Interaction (cs.HC); Applications (stat.AP). Pagina del lavoro: https://arxiv.org/abs/2608.00817 — 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 2026-10-19T09:02:30.748Z dalla pagina https://arxiv.org/catchup/stat.AP/2026-08-11?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).