@inproceedings{zhao-etal-2024-longagent,
title = "{LONGAGENT}: Achieving Question Answering for 128k-Token-Long Documents through Multi-Agent Collaboration",
author = "Zhao, Jun and
Zu, Can and
Hao, Xu and
Lu, Yi and
He, Wei and
Ding, Yiwen and
Gui, Tao and
Zhang, Qi and
Huang, Xuanjing",
editor = "Al-Onaizan, Yaser and
Bansal, Mohit and
Chen, Yun-Nung",
booktitle = "Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing",
month = nov,
year = "2024",
address = "Miami, Florida, USA",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2024.emnlp-main.912",
doi = "10.18653/v1/2024.emnlp-main.912",
pages = "16310--16324",
abstract = "Large language models (LLMs) have achieved tremendous success in understanding language and processing text. However, question-answering (QA) on lengthy documents faces challenges of resource constraints and a high propensity for errors, even for the most advanced models such as GPT-4 and Claude2.In this paper, we introduce {\_}LongAgent{\_}, a multi-agent collaboration method that enables efficient and effective QA over $128k$-token-long documents. {\_}LongAgent{\_} adopts a {\_}divide-and-conquer{\_} strategy, breaking down lengthy documents into shorter, more manageable text chunks. A leader agent comprehends the user{'}s query and organizes the member agents to read their assigned chunks, reasoning a final answer through multiple rounds of discussion.Due to members{'} hallucinations, it{'}s difficult to guarantee that every response provided by each member is accurate.To address this, we develop an {\_}inter-member communication{\_} mechanism that facilitates information sharing, allowing for the detection and mitigation of hallucinatory responses.Experimental results show that a LLaMA-2 7B driven by {\_}LongAgent{\_} can effectively support QA over $128k$-token documents, achieving 16.42{\%} and 1.63{\%} accuracy gains over GPT-4 on single-hop and multi-hop QA settings, respectively.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="zhao-etal-2024-longagent">
<titleInfo>
<title>LONGAGENT: Achieving Question Answering for 128k-Token-Long Documents through Multi-Agent Collaboration</title>
</titleInfo>
<name type="personal">
<namePart type="given">Jun</namePart>
<namePart type="family">Zhao</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Can</namePart>
<namePart type="family">Zu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Xu</namePart>
<namePart type="family">Hao</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yi</namePart>
<namePart type="family">Lu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Wei</namePart>
<namePart type="family">He</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yiwen</namePart>
<namePart type="family">Ding</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Tao</namePart>
<namePart type="family">Gui</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Qi</namePart>
<namePart type="family">Zhang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Xuanjing</namePart>
<namePart type="family">Huang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2024-11</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing</title>
</titleInfo>
<name type="personal">
<namePart type="given">Yaser</namePart>
<namePart type="family">Al-Onaizan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mohit</namePart>
<namePart type="family">Bansal</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yun-Nung</namePart>
<namePart type="family">Chen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Miami, Florida, USA</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Large language models (LLMs) have achieved tremendous success in understanding language and processing text. However, question-answering (QA) on lengthy documents faces challenges of resource constraints and a high propensity for errors, even for the most advanced models such as GPT-4 and Claude2.In this paper, we introduce _LongAgent_, a multi-agent collaboration method that enables efficient and effective QA over 128k-token-long documents. _LongAgent_ adopts a _divide-and-conquer_ strategy, breaking down lengthy documents into shorter, more manageable text chunks. A leader agent comprehends the user’s query and organizes the member agents to read their assigned chunks, reasoning a final answer through multiple rounds of discussion.Due to members’ hallucinations, it’s difficult to guarantee that every response provided by each member is accurate.To address this, we develop an _inter-member communication_ mechanism that facilitates information sharing, allowing for the detection and mitigation of hallucinatory responses.Experimental results show that a LLaMA-2 7B driven by _LongAgent_ can effectively support QA over 128k-token documents, achieving 16.42% and 1.63% accuracy gains over GPT-4 on single-hop and multi-hop QA settings, respectively.</abstract>
<identifier type="citekey">zhao-etal-2024-longagent</identifier>
<identifier type="doi">10.18653/v1/2024.emnlp-main.912</identifier>
<location>
<url>https://aclanthology.org/2024.emnlp-main.912</url>
</location>
<part>
<date>2024-11</date>
<extent unit="page">
<start>16310</start>
<end>16324</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T LONGAGENT: Achieving Question Answering for 128k-Token-Long Documents through Multi-Agent Collaboration
%A Zhao, Jun
%A Zu, Can
%A Hao, Xu
%A Lu, Yi
%A He, Wei
%A Ding, Yiwen
%A Gui, Tao
%A Zhang, Qi
%A Huang, Xuanjing
%Y Al-Onaizan, Yaser
%Y Bansal, Mohit
%Y Chen, Yun-Nung
%S Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing
%D 2024
%8 November
%I Association for Computational Linguistics
%C Miami, Florida, USA
%F zhao-etal-2024-longagent
%X Large language models (LLMs) have achieved tremendous success in understanding language and processing text. However, question-answering (QA) on lengthy documents faces challenges of resource constraints and a high propensity for errors, even for the most advanced models such as GPT-4 and Claude2.In this paper, we introduce _LongAgent_, a multi-agent collaboration method that enables efficient and effective QA over 128k-token-long documents. _LongAgent_ adopts a _divide-and-conquer_ strategy, breaking down lengthy documents into shorter, more manageable text chunks. A leader agent comprehends the user’s query and organizes the member agents to read their assigned chunks, reasoning a final answer through multiple rounds of discussion.Due to members’ hallucinations, it’s difficult to guarantee that every response provided by each member is accurate.To address this, we develop an _inter-member communication_ mechanism that facilitates information sharing, allowing for the detection and mitigation of hallucinatory responses.Experimental results show that a LLaMA-2 7B driven by _LongAgent_ can effectively support QA over 128k-token documents, achieving 16.42% and 1.63% accuracy gains over GPT-4 on single-hop and multi-hop QA settings, respectively.
%R 10.18653/v1/2024.emnlp-main.912
%U https://aclanthology.org/2024.emnlp-main.912
%U https://doi.org/10.18653/v1/2024.emnlp-main.912
%P 16310-16324
Markdown (Informal)
[LONGAGENT: Achieving Question Answering for 128k-Token-Long Documents through Multi-Agent Collaboration](https://aclanthology.org/2024.emnlp-main.912) (Zhao et al., EMNLP 2024)
ACL
- Jun Zhao, Can Zu, Xu Hao, Yi Lu, Wei He, Yiwen Ding, Tao Gui, Qi Zhang, and Xuanjing Huang. 2024. LONGAGENT: Achieving Question Answering for 128k-Token-Long Documents through Multi-Agent Collaboration. In Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing, pages 16310–16324, Miami, Florida, USA. Association for Computational Linguistics.