Evaluating large language models for quality control in research ethics review
Abstract Large Language Models (LLMs) could streamline research ethics and governance review by automating routine quality control checks. This study assessed Claude 3.5 Sonnet, ChatGPT4o, and Microsoft CoPilot in evaluating participant information sheets against Health Research Authority standards. Six clinical trial applications were processed using 32 standardised queries, with accuracy, processing time, error rates, and response quality assessed by two blinded reviewers. Claude showed the highest accuracy, detected more deviations from guidance, and had the fastest processing time (7.17 ± 0.68 min vs. ChatGPT 13.58 ± 2.2 min, CoPilot 23.25 ± 6.21 min). Hallucination rates were lowest in Claude, followed by ChatGPT and CoPilot. Claude also received the highest response quality ratings (77.6% “very good” vs. ChatGPT 56.7%, CoPilot 45.2%). While all three models were capable, Claude consistently outperformed the others, demonstrating the potential of LLM-assisted quality control while emphasizing the need for human oversight.
Authors
- Simon Erik Kolstoe (ORCID: https://orcid.org/0000-0003-1472-3966)
- Pearse Andrew Keane (ORCID: https://orcid.org/0000-0002-9239-745X)
- Zoher Kapacee (ORCID: https://orcid.org/0009-0007-8888-3264)
- Jonathan Fennelly-Barnwell
- Xiaoxuan Liu (ORCID: https://orcid.org/0000-0002-1286-0038)
- Panagiotis Maghsoudlou (ORCID: https://orcid.org/0000-0002-9945-3901)
- A. Abraham (ORCID: https://orcid.org/0000-0002-5679-3535)
- Sunil Mamtora (ORCID: https://orcid.org/0000-0002-1718-8973)
- Alastair Keith Denniston (ORCID: https://orcid.org/0000-0001-7849-0087)
- Ashley Totenhofer
Institutions
- University Hospitals Birmingham NHS Foundation Trust (GB)
- Moorfields Eye Hospital NHS Foundation Trust (GB)
- University of Bristol (GB)
- NIHR Moorfields Biomedical Research Centre (GB)
- UCL Biomedical Research Centre (GB)
- Health Research Authority (GB)
- University College London (GB)
- University of Portsmouth (GB)
- University of Birmingham (GB)
Publication Details
- Journal
- Scientific Reports
- Published
- 2026-11-16
- DOI
- https://doi.org/10.1038/s41598-026-62027-y
- Citations
- 2
- Primary Topic
- Artificial Intelligence in Healthcare and Education
- Type
- article
- Field-Weighted Citation Impact
- 2.03