@inproceedings{lu-kao-2024-0x,
title = "0x.{Y}uan at {S}em{E}val-2024 Task 2: Agents Debating can reach consensus and produce better outcomes in Medical {NLI} task",
author = "Lu, Yu-an and
Kao, Hung-yu",
editor = {Ojha, Atul Kr. and
Do{\u{g}}ru{\"o}z, A. Seza and
Tayyar Madabushi, Harish and
Da San Martino, Giovanni and
Rosenthal, Sara and
Ros{\'a}, Aiala},
booktitle = "Proceedings of the 18th International Workshop on Semantic Evaluation (SemEval-2024)",
month = jun,
year = "2024",
address = "Mexico City, Mexico",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2024.semeval-1.47",
doi = "10.18653/v1/2024.semeval-1.47",
pages = "305--310",
abstract = "In this paper, we introduce a multi-agent debating framework, experimenting on SemEval 2024 Task 2. This innovative system employs a collaborative approach involving expert agents from various medical fields to analyze Clinical Trial Reports (CTRs). Our methodology emphasizes nuanced and comprehensive analysis by leveraging the diverse expertise of agents like Biostatisticians and Medical Linguists. Results indicate that our collaborative model surpasses the performance of individual agents in terms of Macro F1-score. Additionally, our analysis suggests that while initial debates often mirror majority decisions, the debating process refines these outcomes, demonstrating the system{'}s capability for in-depth analysis beyond simple majority rule. This research highlights the potential of AI collaboration in specialized domains, particularly in medical text interpretation.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="lu-kao-2024-0x">
<titleInfo>
<title>0x.Yuan at SemEval-2024 Task 2: Agents Debating can reach consensus and produce better outcomes in Medical NLI task</title>
</titleInfo>
<name type="personal">
<namePart type="given">Yu-an</namePart>
<namePart type="family">Lu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hung-yu</namePart>
<namePart type="family">Kao</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2024-06</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 18th International Workshop on Semantic Evaluation (SemEval-2024)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Atul</namePart>
<namePart type="given">Kr.</namePart>
<namePart type="family">Ojha</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">A</namePart>
<namePart type="given">Seza</namePart>
<namePart type="family">Doğruöz</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Harish</namePart>
<namePart type="family">Tayyar Madabushi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Giovanni</namePart>
<namePart type="family">Da San Martino</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sara</namePart>
<namePart type="family">Rosenthal</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Aiala</namePart>
<namePart type="family">Rosá</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Mexico City, Mexico</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>In this paper, we introduce a multi-agent debating framework, experimenting on SemEval 2024 Task 2. This innovative system employs a collaborative approach involving expert agents from various medical fields to analyze Clinical Trial Reports (CTRs). Our methodology emphasizes nuanced and comprehensive analysis by leveraging the diverse expertise of agents like Biostatisticians and Medical Linguists. Results indicate that our collaborative model surpasses the performance of individual agents in terms of Macro F1-score. Additionally, our analysis suggests that while initial debates often mirror majority decisions, the debating process refines these outcomes, demonstrating the system’s capability for in-depth analysis beyond simple majority rule. This research highlights the potential of AI collaboration in specialized domains, particularly in medical text interpretation.</abstract>
<identifier type="citekey">lu-kao-2024-0x</identifier>
<identifier type="doi">10.18653/v1/2024.semeval-1.47</identifier>
<location>
<url>https://aclanthology.org/2024.semeval-1.47</url>
</location>
<part>
<date>2024-06</date>
<extent unit="page">
<start>305</start>
<end>310</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T 0x.Yuan at SemEval-2024 Task 2: Agents Debating can reach consensus and produce better outcomes in Medical NLI task
%A Lu, Yu-an
%A Kao, Hung-yu
%Y Ojha, Atul Kr.
%Y Doğruöz, A. Seza
%Y Tayyar Madabushi, Harish
%Y Da San Martino, Giovanni
%Y Rosenthal, Sara
%Y Rosá, Aiala
%S Proceedings of the 18th International Workshop on Semantic Evaluation (SemEval-2024)
%D 2024
%8 June
%I Association for Computational Linguistics
%C Mexico City, Mexico
%F lu-kao-2024-0x
%X In this paper, we introduce a multi-agent debating framework, experimenting on SemEval 2024 Task 2. This innovative system employs a collaborative approach involving expert agents from various medical fields to analyze Clinical Trial Reports (CTRs). Our methodology emphasizes nuanced and comprehensive analysis by leveraging the diverse expertise of agents like Biostatisticians and Medical Linguists. Results indicate that our collaborative model surpasses the performance of individual agents in terms of Macro F1-score. Additionally, our analysis suggests that while initial debates often mirror majority decisions, the debating process refines these outcomes, demonstrating the system’s capability for in-depth analysis beyond simple majority rule. This research highlights the potential of AI collaboration in specialized domains, particularly in medical text interpretation.
%R 10.18653/v1/2024.semeval-1.47
%U https://aclanthology.org/2024.semeval-1.47
%U https://doi.org/10.18653/v1/2024.semeval-1.47
%P 305-310
Markdown (Informal)
[0x.Yuan at SemEval-2024 Task 2: Agents Debating can reach consensus and produce better outcomes in Medical NLI task](https://aclanthology.org/2024.semeval-1.47) (Lu & Kao, SemEval 2024)
ACL