KRAGEN: a knowledge graph-enhanced RAG framework for biomedical problem solving using large language models
Bioinformatics · 03.06.2024 · 40 (6)
DOI: 10.1093/bioinformatics/btae353 ↗Kurz gefasst
Fachartikel in der Zeitschrift Bioinformatics, online erschienen am 03.06.2024. Verfasst von Nicholas Matsumoto und 6 weiteren Autor:innen. Beteiligte Einrichtung: Department of Computational Biomedicine, Center for Artificial Intelligence Research and Education, Cedars Sinai Medical Center, West Hollywood, CA 9…. Hauptthemen laut MEDLINE: Software. Die Arbeit wurde bisher 126-mal zitiert (Crossref) und nennt 12 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: NLM NIH HHS, NIA NIH HHS, National Institutes of Health USA.
Abstract (Originalsprache)
Motivation Answering and solving complex problems using a large language model (LLM) given a certain domain such as biomedicine is a challenging task that requires both factual consistency and logic, and LLMs often suffer from some major limitations, such as hallucinating false or irrelevant information, or being influenced by noisy data. These issues can compromise the trustworthiness, accuracy, and compliance of LLM-generated text and insights. Results Knowledge Retrieval Augmented Generation ENgine (KRAGEN) is a new tool that combines knowledge graphs, Retrieval Augmented Generation (RAG), and advanced prompting techniques to solve complex problems with natural language. KRAGEN converts knowledge graphs into a vector database and uses RAG to retrieve relevant facts from it. KRAGEN uses advanced prompting techniques: namely graph-of-thoughts (GoT), to dynamically break down a complex problem into smaller subproblems, and proceeds to solve each subproblem by using the relevant knowledge through the RAG framework, which limits the hallucinations, and finally, consolidates the subproblems and provides a solution. KRAGEN’s graph visualization allows the user to interact with and evaluate the quality of the solution’s GoT structure and logic. Availability and implementation KRAGEN is deployed by running its custom Docker containers. KRAGEN is available as open-source from GitHub at: https://github.com/EpistasisLab/KRAGEN.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Autor:innen und Institutionen
- Department of Computational Biomedicine, Center for Artificial Intelligence Research and Education, Cedars Sinai Medical Center, West Hollywood, CA 90069, United States.
ORCID-Profile: Jason H Moore
Förderung
- NLM NIH HHS
- NIA NIH HHS
- National Institutes of Health USA
Zitieren
APA
Matsumoto, N., Moran, J., Choi, H., Hernandez, M. E., Venkatesan, M., Wang, P., & Moore, J. H. (2024). KRAGEN: a knowledge graph-enhanced RAG framework for biomedical problem solving using large language models. Bioinformatics, 40(6). https://doi.org/10.1093/bioinformatics/btae353
Vancouver
Matsumoto N, Moran J, Choi H, Hernandez ME, Venkatesan M, Wang P, et al. KRAGEN: a knowledge graph-enhanced RAG framework for biomedical problem solving using large language models. Bioinformatics. 2024;40(6). doi:10.1093/bioinformatics/btae353
BibTeX
@article{Matsumoto2024,
author = {Matsumoto, Nicholas and Moran, Jay and Choi, Hyunjun and Hernandez, Miguel E and Venkatesan, Mythreye and Wang, Paul and Moore, Jason H},
title = {KRAGEN: a knowledge graph-enhanced RAG framework for biomedical problem solving using large language models},
journal = {Bioinformatics},
year = {2024},
volume = {40},
number = {6},
doi = {10.1093/bioinformatics/btae353}
}
EUVIMED