@inproceedings{sun-etal-2025-enhancing-retrieval,
title = "Enhancing Retrieval-Augmented Generation via Evidence Tree Search",
author = "Sun, Hao and
Cai, Hengyi and
Li, Yuchen and
Fan, Xuanbo and
Wei, Xiaochi and
Wang, Shuaiqiang and
Zhang, Yan and
Yin, Dawei",
editor = "Che, Wanxiang and
Nabende, Joyce and
Shutova, Ekaterina and
Pilehvar, Mohammad Taher",
booktitle = "Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)",
month = jul,
year = "2025",
address = "Vienna, Austria",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2025.acl-long.1175/",
doi = "10.18653/v1/2025.acl-long.1175",
pages = "24116--24127",
ISBN = "979-8-89176-251-0",
abstract = "Retrieval-Augmented Generation (RAG) is widely used to enhance Large Language Models (LLMs) by grounding responses in external knowledge. However, in real-world applications, retrievers often return lengthy documents with redundant or irrelevant content, confusing downstream readers. While evidence retrieval aims to address this by extracting key information, it faces critical challenges: (1) inability to model synergistic inter-dependencies among evidence sentences, (2) lack of supervision for evaluating multi-sentence evidence quality, and (3) computational inefficiency in navigating exponentially growing search spaces of candidate evidence sets. To tackle these challenges, we propose ETS (Evidence Tree Search), a novel framework that reformulates evidence retrieval as a dynamic tree expansion process. Our approach first constructs an evidence tree where each path represents a candidate evidence set, explicitly modeling inter-sentence dependencies through context-aware node selection. We then leverage Monte Carlo Tree Search (MCTS) to efficiently assess evidence quality and introduce an Early-Terminating Beam Search strategy to efficiently accelerate the model inference. Extensive experiments on five datasets demonstrate that ETS significantly outperforms existing methods across different readers. Our code and datasets will be released to facilitate future research."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="sun-etal-2025-enhancing-retrieval">
<titleInfo>
<title>Enhancing Retrieval-Augmented Generation via Evidence Tree Search</title>
</titleInfo>
<name type="personal">
<namePart type="given">Hao</namePart>
<namePart type="family">Sun</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hengyi</namePart>
<namePart type="family">Cai</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yuchen</namePart>
<namePart type="family">Li</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Xuanbo</namePart>
<namePart type="family">Fan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Xiaochi</namePart>
<namePart type="family">Wei</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Shuaiqiang</namePart>
<namePart type="family">Wang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yan</namePart>
<namePart type="family">Zhang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Dawei</namePart>
<namePart type="family">Yin</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 1: Long Papers)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Wanxiang</namePart>
<namePart type="family">Che</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Joyce</namePart>
<namePart type="family">Nabende</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ekaterina</namePart>
<namePart type="family">Shutova</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mohammad</namePart>
<namePart type="given">Taher</namePart>
<namePart type="family">Pilehvar</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">979-8-89176-251-0</identifier>
</relatedItem>
<abstract>Retrieval-Augmented Generation (RAG) is widely used to enhance Large Language Models (LLMs) by grounding responses in external knowledge. However, in real-world applications, retrievers often return lengthy documents with redundant or irrelevant content, confusing downstream readers. While evidence retrieval aims to address this by extracting key information, it faces critical challenges: (1) inability to model synergistic inter-dependencies among evidence sentences, (2) lack of supervision for evaluating multi-sentence evidence quality, and (3) computational inefficiency in navigating exponentially growing search spaces of candidate evidence sets. To tackle these challenges, we propose ETS (Evidence Tree Search), a novel framework that reformulates evidence retrieval as a dynamic tree expansion process. Our approach first constructs an evidence tree where each path represents a candidate evidence set, explicitly modeling inter-sentence dependencies through context-aware node selection. We then leverage Monte Carlo Tree Search (MCTS) to efficiently assess evidence quality and introduce an Early-Terminating Beam Search strategy to efficiently accelerate the model inference. Extensive experiments on five datasets demonstrate that ETS significantly outperforms existing methods across different readers. Our code and datasets will be released to facilitate future research.</abstract>
<identifier type="citekey">sun-etal-2025-enhancing-retrieval</identifier>
<identifier type="doi">10.18653/v1/2025.acl-long.1175</identifier>
<location>
<url>https://aclanthology.org/2025.acl-long.1175/</url>
</location>
<part>
<date>2025-07</date>
<extent unit="page">
<start>24116</start>
<end>24127</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Enhancing Retrieval-Augmented Generation via Evidence Tree Search
%A Sun, Hao
%A Cai, Hengyi
%A Li, Yuchen
%A Fan, Xuanbo
%A Wei, Xiaochi
%A Wang, Shuaiqiang
%A Zhang, Yan
%A Yin, Dawei
%Y Che, Wanxiang
%Y Nabende, Joyce
%Y Shutova, Ekaterina
%Y Pilehvar, Mohammad Taher
%S Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)
%D 2025
%8 July
%I Association for Computational Linguistics
%C Vienna, Austria
%@ 979-8-89176-251-0
%F sun-etal-2025-enhancing-retrieval
%X Retrieval-Augmented Generation (RAG) is widely used to enhance Large Language Models (LLMs) by grounding responses in external knowledge. However, in real-world applications, retrievers often return lengthy documents with redundant or irrelevant content, confusing downstream readers. While evidence retrieval aims to address this by extracting key information, it faces critical challenges: (1) inability to model synergistic inter-dependencies among evidence sentences, (2) lack of supervision for evaluating multi-sentence evidence quality, and (3) computational inefficiency in navigating exponentially growing search spaces of candidate evidence sets. To tackle these challenges, we propose ETS (Evidence Tree Search), a novel framework that reformulates evidence retrieval as a dynamic tree expansion process. Our approach first constructs an evidence tree where each path represents a candidate evidence set, explicitly modeling inter-sentence dependencies through context-aware node selection. We then leverage Monte Carlo Tree Search (MCTS) to efficiently assess evidence quality and introduce an Early-Terminating Beam Search strategy to efficiently accelerate the model inference. Extensive experiments on five datasets demonstrate that ETS significantly outperforms existing methods across different readers. Our code and datasets will be released to facilitate future research.
%R 10.18653/v1/2025.acl-long.1175
%U https://aclanthology.org/2025.acl-long.1175/
%U https://doi.org/10.18653/v1/2025.acl-long.1175
%P 24116-24127
Markdown (Informal)
[Enhancing Retrieval-Augmented Generation via Evidence Tree Search](https://aclanthology.org/2025.acl-long.1175/) (Sun et al., ACL 2025)
ACL
- Hao Sun, Hengyi Cai, Yuchen Li, Xuanbo Fan, Xiaochi Wei, Shuaiqiang Wang, Yan Zhang, and Dawei Yin. 2025. Enhancing Retrieval-Augmented Generation via Evidence Tree Search. In Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 24116–24127, Vienna, Austria. Association for Computational Linguistics.