MEGA-RAG: a retrieval-augmented generation framework with multi-evidence guided answer refinement for mitigating hallucinations of LLMs in public health
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.
Authors
- Zhangcai Yan
- Shan Xu (ORCID: https://orcid.org/0000-0003-0754-0969)
- Fan Wu (ORCID: https://orcid.org/0000-0002-8863-3026)
- Cheng Dai (ORCID: https://orcid.org/0000-0002-4763-1016)
Institutions
- The University of Sydney (AU)
- Fudan University (CN)
- China Academy of Information and Communications Technology (CN)
Publication Details
- Journal
- Frontiers in Public Health
- Published
- 2025-10-08
- DOI
- https://doi.org/10.3389/fpubh.2025.1635381
- Citations
- 12
- Primary Topic
- Topic Modeling
- Type
- article
- Field-Weighted Citation Impact
- 29.77