@inproceedings{liang-etal-2025-explain,
title = "{EXPLAIN}: Enhancing Retrieval-Augmented Generation with Entity Summary",
author = "Liang, Yaozhen and
Liu, Xiao and
Yu, Jiajun and
Fang, Zhouhua and
Zou, Qunsheng and
Zheng, Linghan and
Li, Yong and
Liu, Zhiwei and
Wang, Haishuai",
editor = "Rehm, Georg and
Li, Yunyao",
booktitle = "Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 6: Industry Track)",
month = jul,
year = "2025",
address = "Vienna, Austria",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2025.acl-industry.108/",
doi = "10.18653/v1/2025.acl-industry.108",
pages = "1520--1529",
ISBN = "979-8-89176-288-6",
abstract = "Document question answering plays a crucial role in enhancing employee productivity by providing quick and accurate access to information. Two primary approaches have been developed: retrieval-augmented generation (RAG), which reduces input tokens and inference costs, and long-context question answering (LC), which processes entire documents for higher accuracy. We introduce EXPLAIN (\textbf{EX}tracting, \textbf{P}re-summarizing, \textbf{L}inking and enh\textbf{A}c\textbf{IN}g RAG), a novel retrieval-augmented generation method that automatically extracts useful entities and generates summaries from documents. EXPLAIN improves accuracy by retrieving more informative entity summaries, achieving precision comparable to LC while maintaining low token consumption. Experimental results on internal dataset (ROUGE-L from 30.14{\%} to 30.31{\%}) and three public datasets (HotpotQA, 2WikiMQA, and Quality, average score from 62{\%} to 64{\%}) demonstrate the efficacy of EXPLAIN. Human evaluation in ant group production deployment indicates EXPLAIN surpasses baseline RAG in comprehensiveness."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="liang-etal-2025-explain">
<titleInfo>
<title>EXPLAIN: Enhancing Retrieval-Augmented Generation with Entity Summary</title>
</titleInfo>
<name type="personal">
<namePart type="given">Yaozhen</namePart>
<namePart type="family">Liang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Xiao</namePart>
<namePart type="family">Liu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jiajun</namePart>
<namePart type="family">Yu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Zhouhua</namePart>
<namePart type="family">Fang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Qunsheng</namePart>
<namePart type="family">Zou</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Linghan</namePart>
<namePart type="family">Zheng</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yong</namePart>
<namePart type="family">Li</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Zhiwei</namePart>
<namePart type="family">Liu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Haishuai</namePart>
<namePart type="family">Wang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2025-07</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 6: Industry Track)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Georg</namePart>
<namePart type="family">Rehm</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yunyao</namePart>
<namePart type="family">Li</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Vienna, Austria</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-8-89176-288-6</identifier>
</relatedItem>
<abstract>Document question answering plays a crucial role in enhancing employee productivity by providing quick and accurate access to information. Two primary approaches have been developed: retrieval-augmented generation (RAG), which reduces input tokens and inference costs, and long-context question answering (LC), which processes entire documents for higher accuracy. We introduce EXPLAIN (EXtracting, Pre-summarizing, Linking and enhAcINg RAG), a novel retrieval-augmented generation method that automatically extracts useful entities and generates summaries from documents. EXPLAIN improves accuracy by retrieving more informative entity summaries, achieving precision comparable to LC while maintaining low token consumption. Experimental results on internal dataset (ROUGE-L from 30.14% to 30.31%) and three public datasets (HotpotQA, 2WikiMQA, and Quality, average score from 62% to 64%) demonstrate the efficacy of EXPLAIN. Human evaluation in ant group production deployment indicates EXPLAIN surpasses baseline RAG in comprehensiveness.</abstract>
<identifier type="citekey">liang-etal-2025-explain</identifier>
<identifier type="doi">10.18653/v1/2025.acl-industry.108</identifier>
<location>
<url>https://aclanthology.org/2025.acl-industry.108/</url>
</location>
<part>
<date>2025-07</date>
<extent unit="page">
<start>1520</start>
<end>1529</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T EXPLAIN: Enhancing Retrieval-Augmented Generation with Entity Summary
%A Liang, Yaozhen
%A Liu, Xiao
%A Yu, Jiajun
%A Fang, Zhouhua
%A Zou, Qunsheng
%A Zheng, Linghan
%A Li, Yong
%A Liu, Zhiwei
%A Wang, Haishuai
%Y Rehm, Georg
%Y Li, Yunyao
%S Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 6: Industry Track)
%D 2025
%8 July
%I Association for Computational Linguistics
%C Vienna, Austria
%@ 979-8-89176-288-6
%F liang-etal-2025-explain
%X Document question answering plays a crucial role in enhancing employee productivity by providing quick and accurate access to information. Two primary approaches have been developed: retrieval-augmented generation (RAG), which reduces input tokens and inference costs, and long-context question answering (LC), which processes entire documents for higher accuracy. We introduce EXPLAIN (EXtracting, Pre-summarizing, Linking and enhAcINg RAG), a novel retrieval-augmented generation method that automatically extracts useful entities and generates summaries from documents. EXPLAIN improves accuracy by retrieving more informative entity summaries, achieving precision comparable to LC while maintaining low token consumption. Experimental results on internal dataset (ROUGE-L from 30.14% to 30.31%) and three public datasets (HotpotQA, 2WikiMQA, and Quality, average score from 62% to 64%) demonstrate the efficacy of EXPLAIN. Human evaluation in ant group production deployment indicates EXPLAIN surpasses baseline RAG in comprehensiveness.
%R 10.18653/v1/2025.acl-industry.108
%U https://aclanthology.org/2025.acl-industry.108/
%U https://doi.org/10.18653/v1/2025.acl-industry.108
%P 1520-1529
Markdown (Informal)
[EXPLAIN: Enhancing Retrieval-Augmented Generation with Entity Summary](https://aclanthology.org/2025.acl-industry.108/) (Liang et al., ACL 2025)
ACL
- Yaozhen Liang, Xiao Liu, Jiajun Yu, Zhouhua Fang, Qunsheng Zou, Linghan Zheng, Yong Li, Zhiwei Liu, and Haishuai Wang. 2025. EXPLAIN: Enhancing Retrieval-Augmented Generation with Entity Summary. In Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 6: Industry Track), pages 1520–1529, Vienna, Austria. Association for Computational Linguistics.