Skip to main page content
U.S. flag

An official website of the United States government

Dot gov

The .gov means it’s official.
Federal government websites often end in .gov or .mil. Before sharing sensitive information, make sure you’re on a federal government site.

Https

The site is secure.
The https:// ensures that you are connecting to the official website and that any information you provide is encrypted and transmitted securely.

Access keys NCBI Homepage MyNCBI Homepage Main Content Main Navigation
. 2024 Jun 3;40(6):btae353.
doi: 10.1093/bioinformatics/btae353.

KRAGEN: a knowledge graph-enhanced RAG framework for biomedical problem solving using large language models

Nicholas Matsumoto  1 , Jay Moran  1 , Hyunjun Choi  1 , Miguel E Hernandez  1 , Mythreye Venkatesan  1 , Paul Wang  1 , Jason H Moore  1
Affiliations

KRAGEN: a knowledge graph-enhanced RAG framework for biomedical problem solving using large language models

Nicholas Matsumoto et al. Bioinformatics. .

Abstract

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.

PubMed Disclaimer

Conflict of interest statement

None declared.

Figures

Figure 1.
Figure 1.
Application flow chart (above) from extraction of knowledge from a knowledge graph, to converting the knowledge graph dump into a list of natural language statements, vectorizing the knowledge and uploading to a vector database, and deploying the KRAGEN GUI (bottom) where the user can ask elaborate questions and view the Graph-Of-Thoughts prompting to view the intuition and knowledge used to solve the problem.
See this image and copyright information in PMC

References

    1. Besta M, Blach N, Kubicek A. et al. Graph of thoughts: solving elaborate problems with large language models. Proc AAAI Conf AI 2023;38:17682–90.
    1. Brate R, Dang M-H, Hoppe F. et al. Improving language model predictions via prompts enriched with knowledge graphs. In: CEUR Workshop Proceedings. 2022. 10.5445/IR/1000151291. - DOI
    1. Ji Z, Lee N, Frieske R. et al. Survey of hallucination in natural language generation. ACM Comput Surv 2023;55:248. 10.1145/3571730. - DOI
    1. Kojima T, Gu SS, Reid M. et al. Large language models are zero-shot reasoners. In: Proceedings of the 36th International Conference on Neural Information Processing Systems (NIPS '22). Red Hook, NY, USA: Curran Associates Inc., 2022, pp. 22199–213.
    1. Lewis P, Perez E, Piktus A. et al. Retrieval-augmented generation for knowledge-intensive NLP tasks. Adv Neural Inf Process Syst 2020;33:9459–74.

Publication types