🤖 AI Summary
This work addresses the challenge of hallucination in large language models when generating disease-related biomedical associations by proposing a verifiable and reproducible evaluation framework. The framework integrates retrieval-augmented generation (RAG), semantic matching with biomedical ontologies, majority voting across open-source large language models, and self-consistency analysis, thereby overcoming the limitations of traditional exact ontology matching and enabling multi-level semantic validation of generated content. Experimental results demonstrate that this approach significantly enhances the ability to assess the factual accuracy of associations produced by models such as ChatGPT, offering a novel paradigm for evaluating the reliability of biomedical knowledge generation.
📝 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.