@inproceedings{chu-etal-2024-beamaggr,
title = "{B}eam{A}gg{R}: Beam Aggregation Reasoning over Multi-source Knowledge for Multi-hop Question Answering",
author = "Chu, Zheng and
Chen, Jingchang and
Chen, Qianglong and
Wang, Haotian and
Zhu, Kun and
Du, Xiyuan and
Yu, Weijiang and
Liu, Ming and
Qin, Bing",
editor = "Ku, Lun-Wei and
Martins, Andre and
Srikumar, Vivek",
booktitle = "Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)",
month = aug,
year = "2024",
address = "Bangkok, Thailand",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2024.acl-long.67",
pages = "1229--1248",
abstract = "Large language models (LLMs) have demonstrated strong reasoning capabilities.Nevertheless, they still suffer from factual errors when tackling knowledge-intensive tasks.Retrieval-augmented reasoning represents a promising approach.However, significant challenges still persist, including inaccurate and insufficient retrieval for complex questions, as well as difficulty in integrating multi-source knowledge.To address this, we propose Beam Aggregation Reasoning (BeamAggR), a reasoning framework for knowledge-intensive multi-hop QA.BeamAggR explores and prioritizes promising answers at each hop of question.Concretely, we parse the complex questions into trees, which include atom and composite questions, followed by bottom-up reasoning.For atomic questions, the LLM conducts reasoning on multi-source knowledge to get answer candidates.For composite questions, the LLM combines beam candidates, explores multiple reasoning paths through probabilistic aggregation, and prioritizes the most promising trajectory.Extensive experiments on four open-domain multi-hop reasoning datasets show that our method significantly outperforms SOTA methods by 8.5{\%}.Furthermore, our analysis reveals that BeamAggR elicits better knowledge collaboration and answer aggregation.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="chu-etal-2024-beamaggr">
<titleInfo>
<title>BeamAggR: Beam Aggregation Reasoning over Multi-source Knowledge for Multi-hop Question Answering</title>
</titleInfo>
<name type="personal">
<namePart type="given">Zheng</namePart>
<namePart type="family">Chu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jingchang</namePart>
<namePart type="family">Chen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Qianglong</namePart>
<namePart type="family">Chen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Haotian</namePart>
<namePart type="family">Wang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Kun</namePart>
<namePart type="family">Zhu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Xiyuan</namePart>
<namePart type="family">Du</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Weijiang</namePart>
<namePart type="family">Yu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ming</namePart>
<namePart type="family">Liu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Bing</namePart>
<namePart type="family">Qin</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2024-08</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Lun-Wei</namePart>
<namePart type="family">Ku</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Andre</namePart>
<namePart type="family">Martins</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Vivek</namePart>
<namePart type="family">Srikumar</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Bangkok, Thailand</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Large language models (LLMs) have demonstrated strong reasoning capabilities.Nevertheless, they still suffer from factual errors when tackling knowledge-intensive tasks.Retrieval-augmented reasoning represents a promising approach.However, significant challenges still persist, including inaccurate and insufficient retrieval for complex questions, as well as difficulty in integrating multi-source knowledge.To address this, we propose Beam Aggregation Reasoning (BeamAggR), a reasoning framework for knowledge-intensive multi-hop QA.BeamAggR explores and prioritizes promising answers at each hop of question.Concretely, we parse the complex questions into trees, which include atom and composite questions, followed by bottom-up reasoning.For atomic questions, the LLM conducts reasoning on multi-source knowledge to get answer candidates.For composite questions, the LLM combines beam candidates, explores multiple reasoning paths through probabilistic aggregation, and prioritizes the most promising trajectory.Extensive experiments on four open-domain multi-hop reasoning datasets show that our method significantly outperforms SOTA methods by 8.5%.Furthermore, our analysis reveals that BeamAggR elicits better knowledge collaboration and answer aggregation.</abstract>
<identifier type="citekey">chu-etal-2024-beamaggr</identifier>
<location>
<url>https://aclanthology.org/2024.acl-long.67</url>
</location>
<part>
<date>2024-08</date>
<extent unit="page">
<start>1229</start>
<end>1248</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T BeamAggR: Beam Aggregation Reasoning over Multi-source Knowledge for Multi-hop Question Answering
%A Chu, Zheng
%A Chen, Jingchang
%A Chen, Qianglong
%A Wang, Haotian
%A Zhu, Kun
%A Du, Xiyuan
%A Yu, Weijiang
%A Liu, Ming
%A Qin, Bing
%Y Ku, Lun-Wei
%Y Martins, Andre
%Y Srikumar, Vivek
%S Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)
%D 2024
%8 August
%I Association for Computational Linguistics
%C Bangkok, Thailand
%F chu-etal-2024-beamaggr
%X Large language models (LLMs) have demonstrated strong reasoning capabilities.Nevertheless, they still suffer from factual errors when tackling knowledge-intensive tasks.Retrieval-augmented reasoning represents a promising approach.However, significant challenges still persist, including inaccurate and insufficient retrieval for complex questions, as well as difficulty in integrating multi-source knowledge.To address this, we propose Beam Aggregation Reasoning (BeamAggR), a reasoning framework for knowledge-intensive multi-hop QA.BeamAggR explores and prioritizes promising answers at each hop of question.Concretely, we parse the complex questions into trees, which include atom and composite questions, followed by bottom-up reasoning.For atomic questions, the LLM conducts reasoning on multi-source knowledge to get answer candidates.For composite questions, the LLM combines beam candidates, explores multiple reasoning paths through probabilistic aggregation, and prioritizes the most promising trajectory.Extensive experiments on four open-domain multi-hop reasoning datasets show that our method significantly outperforms SOTA methods by 8.5%.Furthermore, our analysis reveals that BeamAggR elicits better knowledge collaboration and answer aggregation.
%U https://aclanthology.org/2024.acl-long.67
%P 1229-1248
Markdown (Informal)
[BeamAggR: Beam Aggregation Reasoning over Multi-source Knowledge for Multi-hop Question Answering](https://aclanthology.org/2024.acl-long.67) (Chu et al., ACL 2024)
ACL
- Zheng Chu, Jingchang Chen, Qianglong Chen, Haotian Wang, Kun Zhu, Xiyuan Du, Weijiang Yu, Ming Liu, and Bing Qin. 2024. BeamAggR: Beam Aggregation Reasoning over Multi-source Knowledge for Multi-hop Question Answering. In Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 1229–1248, Bangkok, Thailand. Association for Computational Linguistics.