@inproceedings{sun-etal-2026-weakly,
title = "Weakly-supervised Argument Mining with Boundary Refinement and Relation Denoising",
author = "Sun, Wei and
Li, Mingxiao and
Davis, Jesse and
Cabrio, Elena and
Villata, Serena and
Moens, Marie-Francine",
editor = "Akhtar, Mubashara and
Aly, Rami and
Cao, Rui and
Christodoulopoulos, Christos and
Cocarascu, Oana and
Guo, Zhijiang and
Mittal, Arpit and
Schlichtkrull, Michael and
Thorne, James and
Vlachos, Andreas",
booktitle = "Proceedings of the Ninth Fact Extraction and {VER}ification Workshop ({FEVER})",
month = mar,
year = "2026",
address = "Rabat, Morocco",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2026.fever-1.1/",
pages = "1--12",
ISBN = "979-8-89176-365-4",
abstract = "Argument mining (AM) involves extracting argument components and predicting relations between them to create argumentative graphs, which are essential for applications requiring argumentative comprehension. To automatically provide high-quality graphs, previous works require a large amount of human-annotated training samples to train AM models. Instead, we leverage a large language model (LLM) to assign pseudo-labels to training samples for reducing reliance on human-annotated training data. However, the training data weakly-labeled by the LLM are too noisy to develop an AM model with reliable performance. In this paper, to improve the model performance, we propose a center-based component detector that refines the boundaries of the detected components and a relation denoiser to deal with noise present in the pseudo-labels when classifying relations between detected components. Experimentally, our AM model improves the boundary detection obtained from the LLM by up to 16{\%} in terms of IoU75 and of the relation classification obtained from the LLM by up to 12{\%} in terms of macro-F1 score. Our AM model achieves new state-of-the-art performance in weakly-supervised AM, showing up to a 6{\%} improvement over the state-of-the-art component detector and up to a 7{\%} improvement over the state-of-the-art relation classifier. Additionally, our model uses less than 20{\%} of human-annotated data to match the performance of state-of-the-art fully-supervised AM models."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="sun-etal-2026-weakly">
<titleInfo>
<title>Weakly-supervised Argument Mining with Boundary Refinement and Relation Denoising</title>
</titleInfo>
<name type="personal">
<namePart type="given">Wei</namePart>
<namePart type="family">Sun</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mingxiao</namePart>
<namePart type="family">Li</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jesse</namePart>
<namePart type="family">Davis</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Elena</namePart>
<namePart type="family">Cabrio</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Serena</namePart>
<namePart type="family">Villata</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Marie-Francine</namePart>
<namePart type="family">Moens</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2026-03</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Ninth Fact Extraction and VERification Workshop (FEVER)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Mubashara</namePart>
<namePart type="family">Akhtar</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Rami</namePart>
<namePart type="family">Aly</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Rui</namePart>
<namePart type="family">Cao</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Christos</namePart>
<namePart type="family">Christodoulopoulos</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Oana</namePart>
<namePart type="family">Cocarascu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Zhijiang</namePart>
<namePart type="family">Guo</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Arpit</namePart>
<namePart type="family">Mittal</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Michael</namePart>
<namePart type="family">Schlichtkrull</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">James</namePart>
<namePart type="family">Thorne</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Andreas</namePart>
<namePart type="family">Vlachos</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Rabat, Morocco</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-8-89176-365-4</identifier>
</relatedItem>
<abstract>Argument mining (AM) involves extracting argument components and predicting relations between them to create argumentative graphs, which are essential for applications requiring argumentative comprehension. To automatically provide high-quality graphs, previous works require a large amount of human-annotated training samples to train AM models. Instead, we leverage a large language model (LLM) to assign pseudo-labels to training samples for reducing reliance on human-annotated training data. However, the training data weakly-labeled by the LLM are too noisy to develop an AM model with reliable performance. In this paper, to improve the model performance, we propose a center-based component detector that refines the boundaries of the detected components and a relation denoiser to deal with noise present in the pseudo-labels when classifying relations between detected components. Experimentally, our AM model improves the boundary detection obtained from the LLM by up to 16% in terms of IoU75 and of the relation classification obtained from the LLM by up to 12% in terms of macro-F1 score. Our AM model achieves new state-of-the-art performance in weakly-supervised AM, showing up to a 6% improvement over the state-of-the-art component detector and up to a 7% improvement over the state-of-the-art relation classifier. Additionally, our model uses less than 20% of human-annotated data to match the performance of state-of-the-art fully-supervised AM models.</abstract>
<identifier type="citekey">sun-etal-2026-weakly</identifier>
<location>
<url>https://aclanthology.org/2026.fever-1.1/</url>
</location>
<part>
<date>2026-03</date>
<extent unit="page">
<start>1</start>
<end>12</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Weakly-supervised Argument Mining with Boundary Refinement and Relation Denoising
%A Sun, Wei
%A Li, Mingxiao
%A Davis, Jesse
%A Cabrio, Elena
%A Villata, Serena
%A Moens, Marie-Francine
%Y Akhtar, Mubashara
%Y Aly, Rami
%Y Cao, Rui
%Y Christodoulopoulos, Christos
%Y Cocarascu, Oana
%Y Guo, Zhijiang
%Y Mittal, Arpit
%Y Schlichtkrull, Michael
%Y Thorne, James
%Y Vlachos, Andreas
%S Proceedings of the Ninth Fact Extraction and VERification Workshop (FEVER)
%D 2026
%8 March
%I Association for Computational Linguistics
%C Rabat, Morocco
%@ 979-8-89176-365-4
%F sun-etal-2026-weakly
%X Argument mining (AM) involves extracting argument components and predicting relations between them to create argumentative graphs, which are essential for applications requiring argumentative comprehension. To automatically provide high-quality graphs, previous works require a large amount of human-annotated training samples to train AM models. Instead, we leverage a large language model (LLM) to assign pseudo-labels to training samples for reducing reliance on human-annotated training data. However, the training data weakly-labeled by the LLM are too noisy to develop an AM model with reliable performance. In this paper, to improve the model performance, we propose a center-based component detector that refines the boundaries of the detected components and a relation denoiser to deal with noise present in the pseudo-labels when classifying relations between detected components. Experimentally, our AM model improves the boundary detection obtained from the LLM by up to 16% in terms of IoU75 and of the relation classification obtained from the LLM by up to 12% in terms of macro-F1 score. Our AM model achieves new state-of-the-art performance in weakly-supervised AM, showing up to a 6% improvement over the state-of-the-art component detector and up to a 7% improvement over the state-of-the-art relation classifier. Additionally, our model uses less than 20% of human-annotated data to match the performance of state-of-the-art fully-supervised AM models.
%U https://aclanthology.org/2026.fever-1.1/
%P 1-12
Markdown (Informal)
[Weakly-supervised Argument Mining with Boundary Refinement and Relation Denoising](https://aclanthology.org/2026.fever-1.1/) (Sun et al., FEVER 2026)
ACL