Too agreeable to be accurate? Sycophancy and diagnostic instability of large language models in medical diagnosis
- DOI
- 10.1016/j.artmed.2026.103516
- Published
- 2026-12
- Container
- Artificial Intelligence in Medicine
- Publisher
- Elsevier BV
- Open access
- unknown
Credibility signals
uncertain Score 64/100 under policy 1.0.0. This is a metadata assessment, not a judgment of the paper's conclusions.
Show all credibility signals
- supportingDOI registered: A matching record was returned by Crossref.
- supportingDOI resolves: A matching record was returned by Crossref.
- not scoredDirectory of Open Access Journals: No matching DOAJ record was present in this response. No allow-list match; this is not evidence of low credibility.
- not scoredMEDLINE indexed: Not checked or no result supplied; no credibility inference made.
- not scoredOpenAlex core source: Not checked or no result supplied; no credibility inference made.
- not scoredKnown publisher allow-list: Not checked or no result supplied; no credibility inference made.
- not scoredROR affiliation: Not checked or no result supplied; no credibility inference made.
- not scoredRetraction Watch retraction: No retraction notice matched this DOI in the deployed snapshot. No matching event found; coverage may be incomplete.
- not scoredRetraction Watch expression of concern: No expression of concern notice matched this DOI in the deployed snapshot. No matching event found; coverage may be incomplete.
- not scoredRetraction Watch correction: No correction notice matched this DOI in the deployed snapshot. No matching event found; coverage may be incomplete.
- not scoredRetraction Watch reinstatement: No reinstatement notice matched this DOI in the deployed snapshot. No matching event found; coverage may be incomplete.
- not scoredOpen access status: Not checked or no result supplied; no credibility inference made.
- not scoredPublication license: Not checked or no result supplied; no credibility inference made.
- not scoredPublication version: A publication version was supplied but is not scored.
- supportingMetadata completeness: All 6 scored descriptive metadata groups are present.
Cite this work
BibTeX
@article{allodium:10.1016/j.artmed.2026.103516,
title = {Too agreeable to be accurate? Sycophancy and diagnostic instability of large language models in medical diagnosis},
author = {Konrad Samsel and Christoffer Dharma and AmirHossein H.M. Rezaei and Aseel Bahakim and Kynthia Ravikumar and Venkat Bhat and Mohammad Amin Kamaleddin and Zahra Shakeri},
year = {2026},
journal = {Artificial Intelligence in Medicine},
doi = {10.1016/j.artmed.2026.103516},
url = {https://doi.org/10.1016/j.artmed.2026.103516}
}RIS
TY - JOUR TI - Too agreeable to be accurate? Sycophancy and diagnostic instability of large language models in medical diagnosis AU - Konrad Samsel AU - Christoffer Dharma AU - AmirHossein H.M. Rezaei AU - Aseel Bahakim AU - Kynthia Ravikumar AU - Venkat Bhat AU - Mohammad Amin Kamaleddin AU - Zahra Shakeri PY - 2026 JO - Artificial Intelligence in Medicine DO - 10.1016/j.artmed.2026.103516 UR - https://doi.org/10.1016/j.artmed.2026.103516 ER -
APA
Samsel, K., Dharma, C., Rezaei, A. H., Bahakim, A., Ravikumar, K., Bhat, V., Kamaleddin, M. A., & Shakeri, Z. (2026). Too agreeable to be accurate? Sycophancy and diagnostic instability of large language models in medical diagnosis. Artificial Intelligence in Medicine. https://doi.org/10.1016/j.artmed.2026.103516
Source records
- crossref · retrieved 2026-09-26T02:29:34.515Z