Knowledge graph–based thought: a knowledge graph–enhanced LLM framework for pan-cancer question answering
GigaScience · 06.01.2025 · 14
DOI: 10.1093/gigascience/giae082 ↗Kurz gefasst
Fachartikel in der Zeitschrift GigaScience, online erschienen am 06.01.2025. Verfasst von Yichun Feng und 5 weiteren Autor:innen. Beteiligte Einrichtung: Hangzhou Institute for Advanced Study, University of Chinese Academy of Sciences, 310024 Hangzhou, China. Hauptthemen laut MEDLINE: Neoplasms. Die Arbeit wurde bisher 48-mal zitiert (Crossref) und nennt 50 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: National Key Research and Development Program of China, Chinese Academy of Sciences, Guangzhou National Laboratory.
Abstract (Originalsprache)
Background
In recent years, large language models (LLMs) have shown promise in various domains, notably in biomedical sciences. However, their real-world application is often limited by issues like erroneous outputs and hallucinatory responses.
Results
We developed the knowledge graph–based thought (KGT) framework, an innovative solution that integrates LLMs with knowledge graphs (KGs) to improve their initial responses by utilizing verifiable information from KGs, thus significantly reducing factual errors in reasoning. The KGT framework demonstrates strong adaptability and performs well across various open-source LLMs. Notably, KGT can facilitate the discovery of new uses for existing drugs through potential drug–cancer associations and can assist in predicting resistance by analyzing relevant biomarkers and genetic mechanisms. To evaluate the knowledge graph question answering task within biomedicine, we utilize a pan-cancer knowledge graph to develop a pan-cancer question answering benchmark, named pan-cancer question answering.
Conclusions
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.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Stichwörter der Autor:innen
Autor:innen und Institutionen
- Hangzhou Institute for Advanced Study, University of Chinese Academy of Sciences, 310024 Hangzhou, China.
- Guangzhou National Laboratory, Guangzhou International Bio Island, 510005 Guangzhou, China.
- Smartquerier Gene Technology (Shanghai) Co., Ltd., 200100 Shanghai, China.
- BYHEALTH Institute of Nutrition & Health, 510663 Guangzhou, China.
- Shanghai Institute of Nutrition and Health, Chinese Academy of Sciences Shanghai, 200030 Shanghai, China.
ORCID-Profile: Yichun Feng
Förderung
- National Key Research and Development Program of China
- Chinese Academy of Sciences
- Guangzhou National Laboratory
Zitieren
APA
Feng, Y., Zhou, L., Ma, C., Zheng, Y., He, R., & Li, Y. (2025). Knowledge graph–based thought: a knowledge graph–enhanced LLM framework for pan-cancer question answering. GigaScience, 14. https://doi.org/10.1093/gigascience/giae082
Vancouver
Feng Y, Zhou L, Ma C, Zheng Y, He R, Li Y. Knowledge graph–based thought: a knowledge graph–enhanced LLM framework for pan-cancer question answering. GigaScience. 2025;14. doi:10.1093/gigascience/giae082
BibTeX
@article{Feng2025,
author = {Feng, Yichun and Zhou, Lu and Ma, Chao and Zheng, Yikai and He, Ruikun and Li, Yixue},
title = {Knowledge graph–based thought: a knowledge graph–enhanced LLM framework for pan-cancer question answering},
journal = {GigaScience},
year = {2025},
volume = {14},
doi = {10.1093/gigascience/giae082}
}
EUVIMED