Protocol for evaluating ChatGPT in biomedical association generation and verification using a RAG-enabled, cross-model majority voting workflow
Abstract
We present a protocol to evaluate ChatGPT's ability to generate disease-centric biomedical associations. It outlines how we generate the associations, validate the biological entities using biomedical ontologies, and verify associations using literature. The protocol includes a self-consistency strategy to assess generative reliability across ChatGPT models. To address ontology exact-match limitations, we provide a use case performing semantic verification through a workflow enabled by Retrieval-Augmented Generation (RAG) powered by open-source large language models (LLMs). This enables LLMs to establish truth over content generated by other LLMs and expose hallucination.
Fields of Study & Subjects
Artificial Intelligence in Healthcare and Education
Machine Learning in Healthcare
Digital Mental Health Interventions
Publication details
- Journal / source
- STAR Protocols
- Publisher
- Elsevier BV
- Volume
- 7
- Issue
- 2
- Pages
- 104533–104533
- Publication date
- 14 May 2026
- Language
- EN