Cargando…

GeneGPT: Augmenting Large Language Models with Domain Tools for Improved Access to Biomedical Information

While large language models (LLMs) have been successfully applied to various tasks, they still face challenges with hallucinations. Augmenting LLMs with domain-specific tools such as database utilities can facilitate easier and more precise access to specialized knowledge. In this paper, we present...

Descripción completa

Detalles Bibliográficos
Autores principales: Jin, Qiao, Yang, Yifan, Chen, Qingyu, Lu, Zhiyong
Formato: Online Artículo Texto
Lenguaje:English
Publicado: Cornell University 2023
Materias:
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC10153281/
https://www.ncbi.nlm.nih.gov/pubmed/37131884
_version_ 1785035900250488832
author Jin, Qiao
Yang, Yifan
Chen, Qingyu
Lu, Zhiyong
author_facet Jin, Qiao
Yang, Yifan
Chen, Qingyu
Lu, Zhiyong
author_sort Jin, Qiao
collection PubMed
description While large language models (LLMs) have been successfully applied to various tasks, they still face challenges with hallucinations. Augmenting LLMs with domain-specific tools such as database utilities can facilitate easier and more precise access to specialized knowledge. In this paper, we present GeneGPT, a novel method for teaching LLMs to use the Web APIs of the National Center for Biotechnology Information (NCBI) for answering genomics questions. Specifically, we prompt Codex to solve the GeneTuring tests with NCBI Web APIs by in-context learning and an augmented decoding algorithm that can detect and execute API calls. Experimental results show that GeneGPT achieves state-of-the-art performance on eight tasks in the GeneTuring benchmark with an average score of 0.83, largely surpassing retrieval-augmented LLMs such as the new Bing (0.44), biomedical LLMs such as BioMedLM (0.08) and BioGPT (0.04), as well as GPT-3 (0.16) and ChatGPT (0.12). Our further analyses suggest that: (1) API demonstrations have good cross-task generalizability and are more useful than documentations for in-context learning; (2) GeneGPT can generalize to longer chains of API calls and answer multi-hop questions in GeneHop, a novel dataset introduced in this work; (3) Different types of errors are enriched in different tasks, providing valuable insights for future improvements.
format Online
Article
Text
id pubmed-10153281
institution National Center for Biotechnology Information
language English
publishDate 2023
publisher Cornell University
record_format MEDLINE/PubMed
spelling pubmed-101532812023-05-03 GeneGPT: Augmenting Large Language Models with Domain Tools for Improved Access to Biomedical Information Jin, Qiao Yang, Yifan Chen, Qingyu Lu, Zhiyong ArXiv Article While large language models (LLMs) have been successfully applied to various tasks, they still face challenges with hallucinations. Augmenting LLMs with domain-specific tools such as database utilities can facilitate easier and more precise access to specialized knowledge. In this paper, we present GeneGPT, a novel method for teaching LLMs to use the Web APIs of the National Center for Biotechnology Information (NCBI) for answering genomics questions. Specifically, we prompt Codex to solve the GeneTuring tests with NCBI Web APIs by in-context learning and an augmented decoding algorithm that can detect and execute API calls. Experimental results show that GeneGPT achieves state-of-the-art performance on eight tasks in the GeneTuring benchmark with an average score of 0.83, largely surpassing retrieval-augmented LLMs such as the new Bing (0.44), biomedical LLMs such as BioMedLM (0.08) and BioGPT (0.04), as well as GPT-3 (0.16) and ChatGPT (0.12). Our further analyses suggest that: (1) API demonstrations have good cross-task generalizability and are more useful than documentations for in-context learning; (2) GeneGPT can generalize to longer chains of API calls and answer multi-hop questions in GeneHop, a novel dataset introduced in this work; (3) Different types of errors are enriched in different tasks, providing valuable insights for future improvements. Cornell University 2023-05-16 /pmc/articles/PMC10153281/ /pubmed/37131884 Text en https://creativecommons.org/licenses/by/4.0/This work is licensed under a Creative Commons Attribution 4.0 International License (https://creativecommons.org/licenses/by/4.0/) , which allows reusers to distribute, remix, adapt, and build upon the material in any medium or format, so long as attribution is given to the creator. The license allows for commercial use.
spellingShingle Article
Jin, Qiao
Yang, Yifan
Chen, Qingyu
Lu, Zhiyong
GeneGPT: Augmenting Large Language Models with Domain Tools for Improved Access to Biomedical Information
title GeneGPT: Augmenting Large Language Models with Domain Tools for Improved Access to Biomedical Information
title_full GeneGPT: Augmenting Large Language Models with Domain Tools for Improved Access to Biomedical Information
title_fullStr GeneGPT: Augmenting Large Language Models with Domain Tools for Improved Access to Biomedical Information
title_full_unstemmed GeneGPT: Augmenting Large Language Models with Domain Tools for Improved Access to Biomedical Information
title_short GeneGPT: Augmenting Large Language Models with Domain Tools for Improved Access to Biomedical Information
title_sort genegpt: augmenting large language models with domain tools for improved access to biomedical information
topic Article
url https://www.ncbi.nlm.nih.gov/pmc/articles/PMC10153281/
https://www.ncbi.nlm.nih.gov/pubmed/37131884
work_keys_str_mv AT jinqiao genegptaugmentinglargelanguagemodelswithdomaintoolsforimprovedaccesstobiomedicalinformation
AT yangyifan genegptaugmentinglargelanguagemodelswithdomaintoolsforimprovedaccesstobiomedicalinformation
AT chenqingyu genegptaugmentinglargelanguagemodelswithdomaintoolsforimprovedaccesstobiomedicalinformation
AT luzhiyong genegptaugmentinglargelanguagemodelswithdomaintoolsforimprovedaccesstobiomedicalinformation