Logo image
Red Teaming Large Language Models for Healthcare
Preprint   Open access

Red Teaming Large Language Models for Healthcare

Vahid Balazadeh, Michael Cooper, David Pellow, Atousa Assadi, Jennifer Bell, Mark Coastworth, Kaivalya Deshpande, Jim Fackler, Gabriel Funingana, Spencer Gable-Cook, …
ArXiV.org
Cornell University
05/01/2025
DOI: 10.48550/arxiv.2505.00467
url
https://doi.org/10.48550/arxiv.2505.00467View
Preprint (Author's original)This preprint has not been evaluated by subject experts through peer review. Preprints may undergo extensive changes and/or become peer-reviewed journal articles. Open Access

Abstract

We present the design process and findings of the pre-conference workshop at the Machine Learning for Healthcare Conference (2024) entitled Red Teaming Large Language Models for Healthcare, which took place on August 15, 2024. Conference participants, comprising a mix of computational and clinical expertise, attempted to discover vulnerabilities -- realistic clinical prompts for which a large language model (LLM) outputs a response that could cause clinical harm. Red-teaming with clinicians enables the identification of LLM vulnerabilities that may not be recognised by LLM developers lacking clinical expertise. We report the vulnerabilities found, categorise them, and present the results of a replication study assessing the vulnerabilities across all LLMs provided.
Computer Science - Artificial Intelligence Computer Science - Computation and Language

Details

Metrics

14 Record Views
Logo image