Hyper-RAG: Combating LLM Hallucinations using Hypergraph-Driven Retrieval-Augmented Generation
This addresses the critical issue of factual inaccuracies in LLMs for high-stakes domains like medical diagnostics, representing a domain-specific incremental improvement.
The paper tackled the problem of LLM hallucinations in medical applications by introducing Hyper-RAG, a hypergraph-driven method that improved accuracy by an average of 12.3% over direct LLM use and outperformed other RAG methods by up to 6.3%.
Large language models (LLMs) have transformed various sectors, including education, finance, and medicine, by enhancing content generation and decision-making processes. However, their integration into the medical field is cautious due to hallucinations, instances where generated content deviates from factual accuracy, potentially leading to adverse outcomes. To address this, we introduce Hyper-RAG, a hypergraph-driven Retrieval-Augmented Generation method that comprehensively captures both pairwise and beyond-pairwise correlations in domain-specific knowledge, thereby mitigating hallucinations. Experiments on the NeurologyCrop dataset with six prominent LLMs demonstrated that Hyper-RAG improves accuracy by an average of 12.3% over direct LLM use and outperforms Graph RAG and Light RAG by 6.3% and 6.0%, respectively. Additionally, Hyper-RAG maintained stable performance with increasing query complexity, unlike existing methods which declined. Further validation across nine diverse datasets showed a 35.5% performance improvement over Light RAG using a selection-based assessment. The lightweight variant, Hyper-RAG-Lite, achieved twice the retrieval speed and a 3.3% performance boost compared with Light RAG. These results confirm Hyper-RAG's effectiveness in enhancing LLM reliability and reducing hallucinations, making it a robust solution for high-stakes applications like medical diagnostics.