Knowledge graph–based thought: a knowledge graph–enhanced LLM framework for pan-cancer question answering
The KGT framework substantially improves the accuracy and utility of LLMs in the biomedical field. This study serves as a proof of concept, demonstrating its exceptional performance in biomedical question answering.
Authors
- Yixue Li (ORCID: https://orcid.org/0000-0002-1198-7176)
- Yichun Feng (ORCID: https://orcid.org/0009-0007-4511-4713)
- Chao Ma (ORCID: https://orcid.org/0000-0002-3325-7318)
- Lu Zhou (ORCID: https://orcid.org/0009-0009-8174-0919)
- Ruikun He
- Yikai Zheng
Institutions
- Guangzhou Experimental Station (CN)
- Shanghai Institute of Nutrition and Health (CN)
- University of Chinese Academy of Sciences (CN)
Publication Details
- Journal
- GigaScience
- Published
- 2024-10-02
- DOI
- https://doi.org/10.1093/gigascience/giae082
- Citations
- 25
- Primary Topic
- Topic Modeling
- Type
- article
- Field-Weighted Citation Impact
- 8.68
Funders
- Chinese Academy of Sciences
- National Key Research and Development Program of China