Retrieval-Augmented Generation with Estimation of Source Reliability
Retrieval-augmented generation (RAG) addresses key limitations of large language models (LLMs), such as hallucinations and outdated knowledge, by incorporating external databases. These databases typically consult multiple sources to encompass up-to-date and various information. However, standard RA...
Gespeichert in:
Hauptverfasser: | , , , , |
---|---|
Format: | Artikel |
Sprache: | eng |
Schlagworte: | |
Online-Zugang: | Volltext bestellen |
Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
container_end_page | |
---|---|
container_issue | |
container_start_page | |
container_title | |
container_volume | |
creator | Hwang, Jeongyeon Park, Junyoung Park, Hyejin Park, Sangdon Ok, Jungseul |
description | Retrieval-augmented generation (RAG) addresses key limitations of large
language models (LLMs), such as hallucinations and outdated knowledge, by
incorporating external databases. These databases typically consult multiple
sources to encompass up-to-date and various information. However, standard RAG
methods often overlook the heterogeneous source reliability in the multi-source
database and retrieve documents solely based on relevance, making them prone to
propagating misinformation. To address this, we propose Reliability-Aware RAG
(RA-RAG) which estimates the reliability of multiple sources and incorporates
this information into both retrieval and aggregation processes. Specifically,
it iteratively estimates source reliability and true answers for a set of
queries with no labelling. Then, it selectively retrieves relevant documents
from a few of reliable sources and aggregates them using weighted majority
voting, where the selective retrieval ensures scalability while not
compromising the performance. We also introduce a benchmark designed to reflect
real-world scenarios with heterogeneous source reliability and demonstrate the
effectiveness of RA-RAG compared to a set of baselines. |
doi_str_mv | 10.48550/arxiv.2410.22954 |
format | Article |
fullrecord | <record><control><sourceid>arxiv_GOX</sourceid><recordid>TN_cdi_arxiv_primary_2410_22954</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><sourcerecordid>2410_22954</sourcerecordid><originalsourceid>FETCH-arxiv_primary_2410_229543</originalsourceid><addsrcrecordid>eNpjYJA0NNAzsTA1NdBPLKrILNMzMgEKGBlZmppwMrgEpZYUZaaWJeboOpam56bmlaSmKLin5qUWJZZk5ucplGeWZCi4Fpdk5kL4-WkKwfmlRcmpCkGpOZmJSZk5mSWVPAysaYk5xam8UJqbQd7NNcTZQxdsX3xBEVB3UWU8yN54sL3GhFUAACjCOKk</addsrcrecordid><sourcetype>Open Access Repository</sourcetype><iscdi>true</iscdi><recordtype>article</recordtype></control><display><type>article</type><title>Retrieval-Augmented Generation with Estimation of Source Reliability</title><source>arXiv.org</source><creator>Hwang, Jeongyeon ; Park, Junyoung ; Park, Hyejin ; Park, Sangdon ; Ok, Jungseul</creator><creatorcontrib>Hwang, Jeongyeon ; Park, Junyoung ; Park, Hyejin ; Park, Sangdon ; Ok, Jungseul</creatorcontrib><description>Retrieval-augmented generation (RAG) addresses key limitations of large
language models (LLMs), such as hallucinations and outdated knowledge, by
incorporating external databases. These databases typically consult multiple
sources to encompass up-to-date and various information. However, standard RAG
methods often overlook the heterogeneous source reliability in the multi-source
database and retrieve documents solely based on relevance, making them prone to
propagating misinformation. To address this, we propose Reliability-Aware RAG
(RA-RAG) which estimates the reliability of multiple sources and incorporates
this information into both retrieval and aggregation processes. Specifically,
it iteratively estimates source reliability and true answers for a set of
queries with no labelling. Then, it selectively retrieves relevant documents
from a few of reliable sources and aggregates them using weighted majority
voting, where the selective retrieval ensures scalability while not
compromising the performance. We also introduce a benchmark designed to reflect
real-world scenarios with heterogeneous source reliability and demonstrate the
effectiveness of RA-RAG compared to a set of baselines.</description><identifier>DOI: 10.48550/arxiv.2410.22954</identifier><language>eng</language><subject>Computer Science - Learning</subject><creationdate>2024-10</creationdate><rights>http://arxiv.org/licenses/nonexclusive-distrib/1.0</rights><oa>free_for_read</oa><woscitedreferencessubscribed>false</woscitedreferencessubscribed></display><links><openurl>$$Topenurl_article</openurl><openurlfulltext>$$Topenurlfull_article</openurlfulltext><thumbnail>$$Tsyndetics_thumb_exl</thumbnail><link.rule.ids>228,230,780,885</link.rule.ids><linktorsrc>$$Uhttps://arxiv.org/abs/2410.22954$$EView_record_in_Cornell_University$$FView_record_in_$$GCornell_University$$Hfree_for_read</linktorsrc><backlink>$$Uhttps://doi.org/10.48550/arXiv.2410.22954$$DView paper in arXiv$$Hfree_for_read</backlink></links><search><creatorcontrib>Hwang, Jeongyeon</creatorcontrib><creatorcontrib>Park, Junyoung</creatorcontrib><creatorcontrib>Park, Hyejin</creatorcontrib><creatorcontrib>Park, Sangdon</creatorcontrib><creatorcontrib>Ok, Jungseul</creatorcontrib><title>Retrieval-Augmented Generation with Estimation of Source Reliability</title><description>Retrieval-augmented generation (RAG) addresses key limitations of large
language models (LLMs), such as hallucinations and outdated knowledge, by
incorporating external databases. These databases typically consult multiple
sources to encompass up-to-date and various information. However, standard RAG
methods often overlook the heterogeneous source reliability in the multi-source
database and retrieve documents solely based on relevance, making them prone to
propagating misinformation. To address this, we propose Reliability-Aware RAG
(RA-RAG) which estimates the reliability of multiple sources and incorporates
this information into both retrieval and aggregation processes. Specifically,
it iteratively estimates source reliability and true answers for a set of
queries with no labelling. Then, it selectively retrieves relevant documents
from a few of reliable sources and aggregates them using weighted majority
voting, where the selective retrieval ensures scalability while not
compromising the performance. We also introduce a benchmark designed to reflect
real-world scenarios with heterogeneous source reliability and demonstrate the
effectiveness of RA-RAG compared to a set of baselines.</description><subject>Computer Science - Learning</subject><fulltext>true</fulltext><rsrctype>article</rsrctype><creationdate>2024</creationdate><recordtype>article</recordtype><sourceid>GOX</sourceid><recordid>eNpjYJA0NNAzsTA1NdBPLKrILNMzMgEKGBlZmppwMrgEpZYUZaaWJeboOpam56bmlaSmKLin5qUWJZZk5ucplGeWZCi4Fpdk5kL4-WkKwfmlRcmpCkGpOZmJSZk5mSWVPAysaYk5xam8UJqbQd7NNcTZQxdsX3xBEVB3UWU8yN54sL3GhFUAACjCOKk</recordid><startdate>20241030</startdate><enddate>20241030</enddate><creator>Hwang, Jeongyeon</creator><creator>Park, Junyoung</creator><creator>Park, Hyejin</creator><creator>Park, Sangdon</creator><creator>Ok, Jungseul</creator><scope>AKY</scope><scope>GOX</scope></search><sort><creationdate>20241030</creationdate><title>Retrieval-Augmented Generation with Estimation of Source Reliability</title><author>Hwang, Jeongyeon ; Park, Junyoung ; Park, Hyejin ; Park, Sangdon ; Ok, Jungseul</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-arxiv_primary_2410_229543</frbrgroupid><rsrctype>articles</rsrctype><prefilter>articles</prefilter><language>eng</language><creationdate>2024</creationdate><topic>Computer Science - Learning</topic><toplevel>online_resources</toplevel><creatorcontrib>Hwang, Jeongyeon</creatorcontrib><creatorcontrib>Park, Junyoung</creatorcontrib><creatorcontrib>Park, Hyejin</creatorcontrib><creatorcontrib>Park, Sangdon</creatorcontrib><creatorcontrib>Ok, Jungseul</creatorcontrib><collection>arXiv Computer Science</collection><collection>arXiv.org</collection></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext_linktorsrc</fulltext></delivery><addata><au>Hwang, Jeongyeon</au><au>Park, Junyoung</au><au>Park, Hyejin</au><au>Park, Sangdon</au><au>Ok, Jungseul</au><format>journal</format><genre>article</genre><ristype>JOUR</ristype><atitle>Retrieval-Augmented Generation with Estimation of Source Reliability</atitle><date>2024-10-30</date><risdate>2024</risdate><abstract>Retrieval-augmented generation (RAG) addresses key limitations of large
language models (LLMs), such as hallucinations and outdated knowledge, by
incorporating external databases. These databases typically consult multiple
sources to encompass up-to-date and various information. However, standard RAG
methods often overlook the heterogeneous source reliability in the multi-source
database and retrieve documents solely based on relevance, making them prone to
propagating misinformation. To address this, we propose Reliability-Aware RAG
(RA-RAG) which estimates the reliability of multiple sources and incorporates
this information into both retrieval and aggregation processes. Specifically,
it iteratively estimates source reliability and true answers for a set of
queries with no labelling. Then, it selectively retrieves relevant documents
from a few of reliable sources and aggregates them using weighted majority
voting, where the selective retrieval ensures scalability while not
compromising the performance. We also introduce a benchmark designed to reflect
real-world scenarios with heterogeneous source reliability and demonstrate the
effectiveness of RA-RAG compared to a set of baselines.</abstract><doi>10.48550/arxiv.2410.22954</doi><oa>free_for_read</oa></addata></record> |
fulltext | fulltext_linktorsrc |
identifier | DOI: 10.48550/arxiv.2410.22954 |
ispartof | |
issn | |
language | eng |
recordid | cdi_arxiv_primary_2410_22954 |
source | arXiv.org |
subjects | Computer Science - Learning |
title | Retrieval-Augmented Generation with Estimation of Source Reliability |
url | https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2025-01-08T07%3A48%3A48IST&url_ver=Z39.88-2004&url_ctx_fmt=infofi/fmt:kev:mtx:ctx&rfr_id=info:sid/primo.exlibrisgroup.com:primo3-Article-arxiv_GOX&rft_val_fmt=info:ofi/fmt:kev:mtx:journal&rft.genre=article&rft.atitle=Retrieval-Augmented%20Generation%20with%20Estimation%20of%20Source%20Reliability&rft.au=Hwang,%20Jeongyeon&rft.date=2024-10-30&rft_id=info:doi/10.48550/arxiv.2410.22954&rft_dat=%3Carxiv_GOX%3E2410_22954%3C/arxiv_GOX%3E%3Curl%3E%3C/url%3E&disable_directlink=true&sfx.directlink=off&sfx.report_link=0&rft_id=info:oai/&rft_id=info:pmid/&rfr_iscdi=true |