@inproceedings{li-etal-2025-evaluating,
title = "Evaluating Self-Generated Documents for Enhancing Retrieval-Augmented Generation with Large Language Models",
author = "Li, Jiatao and
Hu, Xinyu and
Yin, Xunjian and
Wan, Xiaojun",
editor = "Chiruzzo, Luis and
Ritter, Alan and
Wang, Lu",
booktitle = "Findings of the Association for Computational Linguistics: NAACL 2025",
month = apr,
year = "2025",
address = "Albuquerque, New Mexico",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2025.findings-naacl.149/",
doi = "10.18653/v1/2025.findings-naacl.149",
pages = "2741--2775",
ISBN = "979-8-89176-195-7",
abstract = "The integration of documents generated by LLMs themselves (Self-Docs) alongside retrieved documents has emerged as a promising strategy for retrieval-augmented generation systems. However, previous research primarily focuses on optimizing the use of Self-Docs, with their inherent properties remaining underexplored. To bridge this gap, we first investigate the overall effectiveness of Self-Docs, identifying key factors that shape their contribution to RAG performance (RQ1). Building on these insights, we develop a taxonomy grounded in Systemic Functional Linguistics to compare the influence of various Self-Docs categories (RQ2) and explore strategies for combining them with external sources (RQ3). Our findings reveal which types of Self-Docs are most beneficial and offer practical guidelines for leveraging them to achieve significant improvements in knowledge-intensive question answering tasks."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="li-etal-2025-evaluating">
<titleInfo>
<title>Evaluating Self-Generated Documents for Enhancing Retrieval-Augmented Generation with Large Language Models</title>
</titleInfo>
<name type="personal">
<namePart type="given">Jiatao</namePart>
<namePart type="family">Li</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Xinyu</namePart>
<namePart type="family">Hu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Xunjian</namePart>
<namePart type="family">Yin</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Xiaojun</namePart>
<namePart type="family">Wan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2025-04</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Findings of the Association for Computational Linguistics: NAACL 2025</title>
</titleInfo>
<name type="personal">
<namePart type="given">Luis</namePart>
<namePart type="family">Chiruzzo</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Alan</namePart>
<namePart type="family">Ritter</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Lu</namePart>
<namePart type="family">Wang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Albuquerque, New Mexico</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-8-89176-195-7</identifier>
</relatedItem>
<abstract>The integration of documents generated by LLMs themselves (Self-Docs) alongside retrieved documents has emerged as a promising strategy for retrieval-augmented generation systems. However, previous research primarily focuses on optimizing the use of Self-Docs, with their inherent properties remaining underexplored. To bridge this gap, we first investigate the overall effectiveness of Self-Docs, identifying key factors that shape their contribution to RAG performance (RQ1). Building on these insights, we develop a taxonomy grounded in Systemic Functional Linguistics to compare the influence of various Self-Docs categories (RQ2) and explore strategies for combining them with external sources (RQ3). Our findings reveal which types of Self-Docs are most beneficial and offer practical guidelines for leveraging them to achieve significant improvements in knowledge-intensive question answering tasks.</abstract>
<identifier type="citekey">li-etal-2025-evaluating</identifier>
<identifier type="doi">10.18653/v1/2025.findings-naacl.149</identifier>
<location>
<url>https://aclanthology.org/2025.findings-naacl.149/</url>
</location>
<part>
<date>2025-04</date>
<extent unit="page">
<start>2741</start>
<end>2775</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Evaluating Self-Generated Documents for Enhancing Retrieval-Augmented Generation with Large Language Models
%A Li, Jiatao
%A Hu, Xinyu
%A Yin, Xunjian
%A Wan, Xiaojun
%Y Chiruzzo, Luis
%Y Ritter, Alan
%Y Wang, Lu
%S Findings of the Association for Computational Linguistics: NAACL 2025
%D 2025
%8 April
%I Association for Computational Linguistics
%C Albuquerque, New Mexico
%@ 979-8-89176-195-7
%F li-etal-2025-evaluating
%X The integration of documents generated by LLMs themselves (Self-Docs) alongside retrieved documents has emerged as a promising strategy for retrieval-augmented generation systems. However, previous research primarily focuses on optimizing the use of Self-Docs, with their inherent properties remaining underexplored. To bridge this gap, we first investigate the overall effectiveness of Self-Docs, identifying key factors that shape their contribution to RAG performance (RQ1). Building on these insights, we develop a taxonomy grounded in Systemic Functional Linguistics to compare the influence of various Self-Docs categories (RQ2) and explore strategies for combining them with external sources (RQ3). Our findings reveal which types of Self-Docs are most beneficial and offer practical guidelines for leveraging them to achieve significant improvements in knowledge-intensive question answering tasks.
%R 10.18653/v1/2025.findings-naacl.149
%U https://aclanthology.org/2025.findings-naacl.149/
%U https://doi.org/10.18653/v1/2025.findings-naacl.149
%P 2741-2775
Markdown (Informal)
[Evaluating Self-Generated Documents for Enhancing Retrieval-Augmented Generation with Large Language Models](https://aclanthology.org/2025.findings-naacl.149/) (Li et al., Findings 2025)
ACL