ESCARGOT：一种利用大语言模型、动态思维图和生物医学知识图谱来增强推理能力的人工智能代理。

ESCARGOT: an AI agent leveraging large language models, dynamic graph of thoughts, and biomedical knowledge graphs for enhanced reasoning.

作者信息

Matsumoto Nicholas, Choi Hyunjun, Moran Jay, Hernandez Miguel E, Venkatesan Mythreye, Li Xi, Chang Jui-Hsuan, Wang Paul, Moore Jason H

机构信息

Department of Computational Biomedicine, Center for Artificial Intelligence Research and Education, Cedars Sinai Medical Center, West Hollywood, CA 90069, United States.

出版信息

Bioinformatics. 2025 Feb 4;41(2). doi: 10.1093/bioinformatics/btaf031.

DOI:10.1093/bioinformatics/btaf031

PMID:39842860

原文链接:https://pmc.ncbi.nlm.nih.gov/articles/PMC11796095/

Abstract

MOTIVATION

LLMs like GPT-4, despite their advancements, often produce hallucinations and struggle with integrating external knowledge effectively. While Retrieval-Augmented Generation (RAG) attempts to address this by incorporating external information, it faces significant challenges such as context length limitations and imprecise vector similarity search. ESCARGOT aims to overcome these issues by combining LLMs with a dynamic Graph of Thoughts and biomedical knowledge graphs, improving output reliability, and reducing hallucinations.

RESULT

ESCARGOT significantly outperforms industry-standard RAG methods, particularly in open-ended questions that demand high precision. ESCARGOT also offers greater transparency in its reasoning process, allowing for the vetting of both code and knowledge requests, in contrast to the black-box nature of LLM-only or RAG-based approaches.

AVAILABILITY AND IMPLEMENTATION

ESCARGOT is available as a pip package and on GitHub at: https://github.com/EpistasisLab/ESCARGOT.

摘要

动机

像GPT-4这样的大语言模型（LLMs）尽管取得了进展，但经常产生幻觉，并且在有效整合外部知识方面存在困难。虽然检索增强生成（RAG）试图通过纳入外部信息来解决这一问题，但它面临着诸如上下文长度限制和不精确的向量相似性搜索等重大挑战。ESCARGOT旨在通过将大语言模型与动态思维图和生物医学知识图谱相结合来克服这些问题，提高输出可靠性，并减少幻觉。