Mega-Rag

Introduction: The increasing adoption of large language models (LLMs) in public health has raised significant concerns about hallucinations-factually inaccurate or misleading outputs that can compromise clinical communication and policy decisions. Methods: We propose a retrieval-augmented generation framework with multi-evidence guided answer refinement (MEGA-RAG), specifically designed to mitigate hallucinations in public health applications. The framework integrates multi-source evidence retrieval (dense retrieval via FAISS, keyword-based retrieval via BM25, and biomedical knowledge graphs), employs a cross-encoder reranker to ensure semantic relevance, and incorporates a discrepancy-aware refinement module to further enhance factual accuracy. Results: Experimental evaluation demonstrates that MEGA-RAG outperforms four baseline models [PubMedBERT, PubMedGPT, standalone LLM, and LLM with standard retrieval-augmented generation (RAG)], achieving a reduction in hallucination rates by over 40%. It also achieves the highest accuracy (0.7913), precision (0.7541), recall (0.8304), and F1 score (0.7904). Discussion: These findings confirm that MEGA-RAG is highly effective in generating factually reliable and medically accurate responses, thereby enhancing the credibility of AI-generated health information for applications in health education, clinical communication, and evidence-based policy development

Credibility · Health information · MEDLINE · Public health · Public health policy · Machine Learning in Healthcare · Mental Health via Writing · Topic Modeling · Health Policy

• Toward clinical integration of generative AI in mental health

  Open Access•Fabio Frisone, Chiara Pupillo et al.•Frontiers in Public Health•2026

  Add to list

• ChatGPT and the rise of large language models

  Open Access•Luigi De Angelis, Francesco Baglivo et al.•Frontiers in Public Health•2023

  Add to list