@inproceedings{liang-etal-2024-debatrix,
title = "Debatrix: Multi-dimensional Debate Judge with Iterative Chronological Analysis Based on {LLM}",
author = "Liang, Jingcong and
Ye, Rong and
Han, Meng and
Lai, Ruofei and
Zhang, Xinyu and
Huang, Xuanjing and
Wei, Zhongyu",
editor = "Ku, Lun-Wei and
Martins, Andre and
Srikumar, Vivek",
booktitle = "Findings of the Association for Computational Linguistics ACL 2024",
month = aug,
year = "2024",
address = "Bangkok, Thailand and virtual meeting",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2024.findings-acl.868",
pages = "14575--14595",
abstract = "How can we construct an automated debate judge to evaluate an extensive, vibrant, multi-turn debate? This task is challenging, as judging a debate involves grappling with lengthy texts, intricate argument relationships, and multi-dimensional assessments.At the same time, current research mainly focuses on short dialogues, rarely touching upon the evaluation of an entire debate.In this paper, by leveraging Large Language Models (LLMs), we propose Debatrix, which makes the analysis and assessment of multi-turn debates more aligned with majority preferences. Specifically, Debatrix features a vertical, iterative chronological analysis and a horizontal, multi-dimensional evaluation collaboration.To align with real-world debate scenarios, we introduced the PanelBench benchmark, comparing our system{'}s performance to actual debate outcomes.The findings indicate a notable enhancement over directly using LLMs for debate evaluation.Source code and benchmark data are available at https://github.com/ljcleo/debatrix.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="liang-etal-2024-debatrix">
<titleInfo>
<title>Debatrix: Multi-dimensional Debate Judge with Iterative Chronological Analysis Based on LLM</title>
</titleInfo>
<name type="personal">
<namePart type="given">Jingcong</namePart>
<namePart type="family">Liang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Rong</namePart>
<namePart type="family">Ye</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Meng</namePart>
<namePart type="family">Han</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ruofei</namePart>
<namePart type="family">Lai</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Xinyu</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>
<name type="personal">
<namePart type="given">Zhongyu</namePart>
<namePart type="family">Wei</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>Findings of the Association for Computational Linguistics ACL 2024</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 and virtual meeting</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>How can we construct an automated debate judge to evaluate an extensive, vibrant, multi-turn debate? This task is challenging, as judging a debate involves grappling with lengthy texts, intricate argument relationships, and multi-dimensional assessments.At the same time, current research mainly focuses on short dialogues, rarely touching upon the evaluation of an entire debate.In this paper, by leveraging Large Language Models (LLMs), we propose Debatrix, which makes the analysis and assessment of multi-turn debates more aligned with majority preferences. Specifically, Debatrix features a vertical, iterative chronological analysis and a horizontal, multi-dimensional evaluation collaboration.To align with real-world debate scenarios, we introduced the PanelBench benchmark, comparing our system’s performance to actual debate outcomes.The findings indicate a notable enhancement over directly using LLMs for debate evaluation.Source code and benchmark data are available at https://github.com/ljcleo/debatrix.</abstract>
<identifier type="citekey">liang-etal-2024-debatrix</identifier>
<location>
<url>https://aclanthology.org/2024.findings-acl.868</url>
</location>
<part>
<date>2024-08</date>
<extent unit="page">
<start>14575</start>
<end>14595</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Debatrix: Multi-dimensional Debate Judge with Iterative Chronological Analysis Based on LLM
%A Liang, Jingcong
%A Ye, Rong
%A Han, Meng
%A Lai, Ruofei
%A Zhang, Xinyu
%A Huang, Xuanjing
%A Wei, Zhongyu
%Y Ku, Lun-Wei
%Y Martins, Andre
%Y Srikumar, Vivek
%S Findings of the Association for Computational Linguistics ACL 2024
%D 2024
%8 August
%I Association for Computational Linguistics
%C Bangkok, Thailand and virtual meeting
%F liang-etal-2024-debatrix
%X How can we construct an automated debate judge to evaluate an extensive, vibrant, multi-turn debate? This task is challenging, as judging a debate involves grappling with lengthy texts, intricate argument relationships, and multi-dimensional assessments.At the same time, current research mainly focuses on short dialogues, rarely touching upon the evaluation of an entire debate.In this paper, by leveraging Large Language Models (LLMs), we propose Debatrix, which makes the analysis and assessment of multi-turn debates more aligned with majority preferences. Specifically, Debatrix features a vertical, iterative chronological analysis and a horizontal, multi-dimensional evaluation collaboration.To align with real-world debate scenarios, we introduced the PanelBench benchmark, comparing our system’s performance to actual debate outcomes.The findings indicate a notable enhancement over directly using LLMs for debate evaluation.Source code and benchmark data are available at https://github.com/ljcleo/debatrix.
%U https://aclanthology.org/2024.findings-acl.868
%P 14575-14595
Markdown (Informal)
[Debatrix: Multi-dimensional Debate Judge with Iterative Chronological Analysis Based on LLM](https://aclanthology.org/2024.findings-acl.868) (Liang et al., Findings 2024)
ACL