Feng Yichun, Zhou Lu, Ma Chao, Zheng Yikai, He Ruikun, Li Yixue
Hangzhou Institute for Advanced Study, University of Chinese Academy of Sciences, 310024 Hangzhou, China.
Guangzhou National Laboratory, Guangzhou International Bio Island, 510005 Guangzhou, China.
Gigascience. 2025 Jan 6;14. doi: 10.1093/gigascience/giae082.
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.
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.
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.
近年来，大语言模型（LLMs）在各个领域都展现出了潜力，尤其是在生物医学领域。然而，它们在现实世界中的应用常常受到错误输出和幻觉式回答等问题的限制。
我们开发了基于知识图谱的思维（KGT）框架，这是一种创新的解决方案，它将大语言模型与知识图谱（KGs）相结合，通过利用来自知识图谱的可验证信息来改进其初始回答，从而显著减少推理中的事实性错误。KGT框架具有很强的适应性，在各种开源大语言模型上都表现良好。值得注意的是，KGT可以通过潜在的药物-癌症关联促进发现现有药物的新用途，并可以通过分析相关生物标志物和遗传机制来协助预测耐药性。为了评估生物医学领域内的知识图谱问答任务，我们利用一个泛癌知识图谱开发了一个泛癌问答基准，名为泛癌问答。
KGT框架极大地提高了大语言模型在生物医学领域的准确性和实用性。本研究作为一个概念验证，展示了其在生物医学问答中的卓越性能。
