@inproceedings{zhu-etal-2025-mitigating,
title = "Mitigating Lost-in-Retrieval Problems in Retrieval Augmented Multi-Hop Question Answering",
author = "Zhu, Rongzhi and
Liu, Xiangyu and
Sun, Zequn and
Wang, Yiwei and
Hu, Wei",
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.1089/",
doi = "10.18653/v1/2025.acl-long.1089",
pages = "22362--22375",
ISBN = "979-8-89176-251-0",
abstract = "In this paper, we identify a critical problem, ``lost-in-retrieval'', in retrieval-augmented multi-hop question answering (QA): the key entities are missed in LLMs' sub-question decomposition. ``Lost-in-retrieval'' significantly degrades the retrieval performance, which disrupts the reasoning chain and leads to the incorrect answers. To resolve this problem, we propose a progressive retrieval and rewriting method, namely ChainRAG, which sequentially handles each sub-question by completing missing key entities and retrieving relevant sentences from a sentence graph for answer generation. Each step in our retrieval and rewriting process builds upon the previous one, creating a seamless chain that leads to accurate retrieval and answers. Finally, all retrieved sentences and sub-question answers are integrated to generate a comprehensive answer to the original question. We evaluate ChainRAG on three multi-hop QA datasets{---}MuSiQue, 2Wiki, and HotpotQA{---}using three large language models: GPT4o-mini, Qwen2.5-72B, and GLM-4-Plus. Empirical results demonstrate that ChainRAG consistently outperforms baselines in both effectiveness and efficiency."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="zhu-etal-2025-mitigating">
<titleInfo>
<title>Mitigating Lost-in-Retrieval Problems in Retrieval Augmented Multi-Hop Question Answering</title>
</titleInfo>
<name type="personal">
<namePart type="given">Rongzhi</namePart>
<namePart type="family">Zhu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Xiangyu</namePart>
<namePart type="family">Liu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Zequn</namePart>
<namePart type="family">Sun</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yiwei</namePart>
<namePart type="family">Wang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Wei</namePart>
<namePart type="family">Hu</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>In this paper, we identify a critical problem, “lost-in-retrieval”, in retrieval-augmented multi-hop question answering (QA): the key entities are missed in LLMs’ sub-question decomposition. “Lost-in-retrieval” significantly degrades the retrieval performance, which disrupts the reasoning chain and leads to the incorrect answers. To resolve this problem, we propose a progressive retrieval and rewriting method, namely ChainRAG, which sequentially handles each sub-question by completing missing key entities and retrieving relevant sentences from a sentence graph for answer generation. Each step in our retrieval and rewriting process builds upon the previous one, creating a seamless chain that leads to accurate retrieval and answers. Finally, all retrieved sentences and sub-question answers are integrated to generate a comprehensive answer to the original question. We evaluate ChainRAG on three multi-hop QA datasets—MuSiQue, 2Wiki, and HotpotQA—using three large language models: GPT4o-mini, Qwen2.5-72B, and GLM-4-Plus. Empirical results demonstrate that ChainRAG consistently outperforms baselines in both effectiveness and efficiency.</abstract>
<identifier type="citekey">zhu-etal-2025-mitigating</identifier>
<identifier type="doi">10.18653/v1/2025.acl-long.1089</identifier>
<location>
<url>https://aclanthology.org/2025.acl-long.1089/</url>
</location>
<part>
<date>2025-07</date>
<extent unit="page">
<start>22362</start>
<end>22375</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Mitigating Lost-in-Retrieval Problems in Retrieval Augmented Multi-Hop Question Answering
%A Zhu, Rongzhi
%A Liu, Xiangyu
%A Sun, Zequn
%A Wang, Yiwei
%A Hu, Wei
%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 zhu-etal-2025-mitigating
%X In this paper, we identify a critical problem, “lost-in-retrieval”, in retrieval-augmented multi-hop question answering (QA): the key entities are missed in LLMs’ sub-question decomposition. “Lost-in-retrieval” significantly degrades the retrieval performance, which disrupts the reasoning chain and leads to the incorrect answers. To resolve this problem, we propose a progressive retrieval and rewriting method, namely ChainRAG, which sequentially handles each sub-question by completing missing key entities and retrieving relevant sentences from a sentence graph for answer generation. Each step in our retrieval and rewriting process builds upon the previous one, creating a seamless chain that leads to accurate retrieval and answers. Finally, all retrieved sentences and sub-question answers are integrated to generate a comprehensive answer to the original question. We evaluate ChainRAG on three multi-hop QA datasets—MuSiQue, 2Wiki, and HotpotQA—using three large language models: GPT4o-mini, Qwen2.5-72B, and GLM-4-Plus. Empirical results demonstrate that ChainRAG consistently outperforms baselines in both effectiveness and efficiency.
%R 10.18653/v1/2025.acl-long.1089
%U https://aclanthology.org/2025.acl-long.1089/
%U https://doi.org/10.18653/v1/2025.acl-long.1089
%P 22362-22375
Markdown (Informal)
[Mitigating Lost-in-Retrieval Problems in Retrieval Augmented Multi-Hop Question Answering](https://aclanthology.org/2025.acl-long.1089/) (Zhu et al., ACL 2025)
ACL