@inproceedings{guida-etal-2025-llms,
title = "{LLM}s for Argument Mining: Detection, Extraction, and Relationship Classification of pre-defined Arguments in Online Comments",
author = "Guida, Matteo and
Otmakhova, Yulia and
Hovy, Eduard and
Frermann, Lea",
editor = "Kummerfeld, Jonathan K. and
Joshi, Aditya and
Dras, Mark",
booktitle = "Proceedings of the 23rd Annual Workshop of the Australasian Language Technology Association",
month = nov,
year = "2025",
address = "Sydney, Australia",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2025.alta-main.12/",
pages = "176--191",
ISBN = "1834-7037",
abstract = "Automated large-scale analysis of public discussions around contested issues like abortion requires detecting and understanding the use of arguments. While Large Language Models (LLMs) have shown promise in language processing tasks, their performance in mining topic-specific, pre-defined arguments in online comments remains underexplored. We evaluate four state-of-the-art LLMs on three argument mining tasks using datasets comprising over 2,000 opinion comments across six polarizing topics. Quantitative evaluation suggests an overall strong performance across the three tasks, especially for large and fine-tuned LLMs, albeit at a significant environmental cost. However, a detailed error analysis revealed systematic shortcomings on long and nuanced comments and emotionally charged language, raising concerns for downstream applications like content moderation or opinion analysis. Our results highlight both the promise and current limitations of LLMs for automated argument analysis in online comments."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="guida-etal-2025-llms">
<titleInfo>
<title>LLMs for Argument Mining: Detection, Extraction, and Relationship Classification of pre-defined Arguments in Online Comments</title>
</titleInfo>
<name type="personal">
<namePart type="given">Matteo</namePart>
<namePart type="family">Guida</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yulia</namePart>
<namePart type="family">Otmakhova</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Eduard</namePart>
<namePart type="family">Hovy</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Lea</namePart>
<namePart type="family">Frermann</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2025-11</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 23rd Annual Workshop of the Australasian Language Technology Association</title>
</titleInfo>
<name type="personal">
<namePart type="given">Jonathan</namePart>
<namePart type="given">K</namePart>
<namePart type="family">Kummerfeld</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Aditya</namePart>
<namePart type="family">Joshi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mark</namePart>
<namePart type="family">Dras</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Sydney, Australia</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">1834-7037</identifier>
</relatedItem>
<abstract>Automated large-scale analysis of public discussions around contested issues like abortion requires detecting and understanding the use of arguments. While Large Language Models (LLMs) have shown promise in language processing tasks, their performance in mining topic-specific, pre-defined arguments in online comments remains underexplored. We evaluate four state-of-the-art LLMs on three argument mining tasks using datasets comprising over 2,000 opinion comments across six polarizing topics. Quantitative evaluation suggests an overall strong performance across the three tasks, especially for large and fine-tuned LLMs, albeit at a significant environmental cost. However, a detailed error analysis revealed systematic shortcomings on long and nuanced comments and emotionally charged language, raising concerns for downstream applications like content moderation or opinion analysis. Our results highlight both the promise and current limitations of LLMs for automated argument analysis in online comments.</abstract>
<identifier type="citekey">guida-etal-2025-llms</identifier>
<location>
<url>https://aclanthology.org/2025.alta-main.12/</url>
</location>
<part>
<date>2025-11</date>
<extent unit="page">
<start>176</start>
<end>191</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T LLMs for Argument Mining: Detection, Extraction, and Relationship Classification of pre-defined Arguments in Online Comments
%A Guida, Matteo
%A Otmakhova, Yulia
%A Hovy, Eduard
%A Frermann, Lea
%Y Kummerfeld, Jonathan K.
%Y Joshi, Aditya
%Y Dras, Mark
%S Proceedings of the 23rd Annual Workshop of the Australasian Language Technology Association
%D 2025
%8 November
%I Association for Computational Linguistics
%C Sydney, Australia
%@ 1834-7037
%F guida-etal-2025-llms
%X Automated large-scale analysis of public discussions around contested issues like abortion requires detecting and understanding the use of arguments. While Large Language Models (LLMs) have shown promise in language processing tasks, their performance in mining topic-specific, pre-defined arguments in online comments remains underexplored. We evaluate four state-of-the-art LLMs on three argument mining tasks using datasets comprising over 2,000 opinion comments across six polarizing topics. Quantitative evaluation suggests an overall strong performance across the three tasks, especially for large and fine-tuned LLMs, albeit at a significant environmental cost. However, a detailed error analysis revealed systematic shortcomings on long and nuanced comments and emotionally charged language, raising concerns for downstream applications like content moderation or opinion analysis. Our results highlight both the promise and current limitations of LLMs for automated argument analysis in online comments.
%U https://aclanthology.org/2025.alta-main.12/
%P 176-191
Markdown (Informal)
[LLMs for Argument Mining: Detection, Extraction, and Relationship Classification of pre-defined Arguments in Online Comments](https://aclanthology.org/2025.alta-main.12/) (Guida et al., ALTA 2025)
ACL