Large language models improve physician accuracy but lead to false reliance

arXiv:2608.00817v1 Announce Type: new Abstract: 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.

Authors:Tirtha Chanda, Christoph Wies, Franziska Schramm, Carina Nogueira Garcia, Nicolas B. Merl, Martin J. Hetz, Jochen S. Utikal, Phillip Tschandl, Cristian Navarrete-Dechent, Alexander Thiem, Jakob N. Kather, Consortium, Titus J. Brinker

Abstract: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.

Artificial Intelligence (cs.AI); Applications (stat.AP)

arXiv:2608.00817 [cs.AI]

(or arXiv:2608.00817v1 [cs.AI] for this version)

https://doi.org/10.48550/arXiv.2608.00817 arXiv-issued DOI via DataCite (pending registration)

aiqbench analysis

Large language models improve physician accuracy but lead to false reliance

Related coverage