Saved in:
Bibliographic Details
Main Authors: Kim, Dongkyu, Kim, Byoungwook, Han, Donggeon, Eibich, Matouš
Format: Preprint
Published: 2024
Subjects:
Online Access:https://arxiv.org/abs/2410.20878
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866910672979230720
author Kim, Dongkyu
Kim, Byoungwook
Han, Donggeon
Eibich, Matouš
author_facet Kim, Dongkyu
Kim, Byoungwook
Han, Donggeon
Eibich, Matouš
contents Using LLMs (Large Language Models) in conjunction with external documents has made RAG (Retrieval-Augmented Generation) an essential technology. Numerous techniques and modules for RAG are being researched, but their performance can vary across different datasets. Finding RAG modules that perform well on specific datasets is challenging. In this paper, we propose the AutoRAG framework, which automatically identifies suitable RAG modules for a given dataset. AutoRAG explores and approximates the optimal combination of RAG modules for the dataset. Additionally, we share the results of optimizing a dataset using AutoRAG. All experimental results and data are publicly available and can be accessed through our GitHub repository https://github.com/Marker-Inc-Korea/AutoRAG_ARAGOG_Paper .
format Preprint
id arxiv_https___arxiv_org_abs_2410_20878
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle AutoRAG: Automated Framework for optimization of Retrieval Augmented Generation Pipeline
Kim, Dongkyu
Kim, Byoungwook
Han, Donggeon
Eibich, Matouš
Computation and Language
H.4.0
Using LLMs (Large Language Models) in conjunction with external documents has made RAG (Retrieval-Augmented Generation) an essential technology. Numerous techniques and modules for RAG are being researched, but their performance can vary across different datasets. Finding RAG modules that perform well on specific datasets is challenging. In this paper, we propose the AutoRAG framework, which automatically identifies suitable RAG modules for a given dataset. AutoRAG explores and approximates the optimal combination of RAG modules for the dataset. Additionally, we share the results of optimizing a dataset using AutoRAG. All experimental results and data are publicly available and can be accessed through our GitHub repository https://github.com/Marker-Inc-Korea/AutoRAG_ARAGOG_Paper .
title AutoRAG: Automated Framework for optimization of Retrieval Augmented Generation Pipeline
topic Computation and Language
H.4.0
url https://arxiv.org/abs/2410.20878