@inproceedings{charalampous-djouvas-2026-createdebate,
title = "The {C}reate{D}ebate Arguments Dataset: A Large-Scale Naturalistic Corpus for Computational Argumentation",
author = "Charalampous, Antonis and
Djouvas, Constantinos",
editor = "Ortiz Suarez, Pedro and
Burchell, Laurie and
Ljube{\v{s}}i{\'c}, Nikola and
Scherrer, Yves and
Laippala, Veronika and
Dini{\'c}, Vuk and
Vaughan, Thom",
booktitle = "Proceedings of the 13th Web-as-Corpus Workshop",
month = oct,
year = "2026",
address = "Budapest, Hungary",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2026.wac-1.2/",
pages = "8--21",
ISBN = "979-8-89176-481-1",
abstract = "We introduce the CreateDebate Arguments Dataset, a large-scale, unfiltered collection of 383,220 arguments from 7,435 of the most active for/against debates on the CreateDebate online debate platform, spanning 16 years of activity. Unlike existing computational argumentation resources, the dataset combines large scale with hierarchical debate-tree structure, author-assigned stance labels, community vote scores, and relational tags that explicitly mark when one argument disputes another. Because the full dataset is unfiltered, we release it under a gated access agreement and additionally release an openly available, manually curated subset of 84,872 arguments from 578 debates. To demonstrate the dataset{'}s utility, we define two counter-argument retrieval benchmarks on the curated subset: a targeted setting that uses the dispute tag as author-verified ground truth, and a general setting in which any opposing-side argument is a valid counter. Evaluating a BM25 baseline, a frozen bi-encoder, and a fine-tuned bi-encoder, we find consistent but bounded gains from fine-tuning on disputed pairs, a negative effect of debate-level context on within-debate retrieval, and limited cross-task transfer between the targeted and general settings. A qualitative analysis surfaces failure modes specific to naturally occurring debate. The dataset and models are released to the community."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="charalampous-djouvas-2026-createdebate">
<titleInfo>
<title>The CreateDebate Arguments Dataset: A Large-Scale Naturalistic Corpus for Computational Argumentation</title>
</titleInfo>
<name type="personal">
<namePart type="given">Antonis</namePart>
<namePart type="family">Charalampous</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Constantinos</namePart>
<namePart type="family">Djouvas</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2026-10</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 13th Web-as-Corpus Workshop</title>
</titleInfo>
<name type="personal">
<namePart type="given">Pedro</namePart>
<namePart type="family">Ortiz Suarez</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Laurie</namePart>
<namePart type="family">Burchell</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Nikola</namePart>
<namePart type="family">Ljubešić</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yves</namePart>
<namePart type="family">Scherrer</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Veronika</namePart>
<namePart type="family">Laippala</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Vuk</namePart>
<namePart type="family">Dinić</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Thom</namePart>
<namePart type="family">Vaughan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Budapest, Hungary</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-8-89176-481-1</identifier>
</relatedItem>
<abstract>We introduce the CreateDebate Arguments Dataset, a large-scale, unfiltered collection of 383,220 arguments from 7,435 of the most active for/against debates on the CreateDebate online debate platform, spanning 16 years of activity. Unlike existing computational argumentation resources, the dataset combines large scale with hierarchical debate-tree structure, author-assigned stance labels, community vote scores, and relational tags that explicitly mark when one argument disputes another. Because the full dataset is unfiltered, we release it under a gated access agreement and additionally release an openly available, manually curated subset of 84,872 arguments from 578 debates. To demonstrate the dataset’s utility, we define two counter-argument retrieval benchmarks on the curated subset: a targeted setting that uses the dispute tag as author-verified ground truth, and a general setting in which any opposing-side argument is a valid counter. Evaluating a BM25 baseline, a frozen bi-encoder, and a fine-tuned bi-encoder, we find consistent but bounded gains from fine-tuning on disputed pairs, a negative effect of debate-level context on within-debate retrieval, and limited cross-task transfer between the targeted and general settings. A qualitative analysis surfaces failure modes specific to naturally occurring debate. The dataset and models are released to the community.</abstract>
<identifier type="citekey">charalampous-djouvas-2026-createdebate</identifier>
<location>
<url>https://aclanthology.org/2026.wac-1.2/</url>
</location>
<part>
<date>2026-10</date>
<extent unit="page">
<start>8</start>
<end>21</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T The CreateDebate Arguments Dataset: A Large-Scale Naturalistic Corpus for Computational Argumentation
%A Charalampous, Antonis
%A Djouvas, Constantinos
%Y Ortiz Suarez, Pedro
%Y Burchell, Laurie
%Y Ljubešić, Nikola
%Y Scherrer, Yves
%Y Laippala, Veronika
%Y Dinić, Vuk
%Y Vaughan, Thom
%S Proceedings of the 13th Web-as-Corpus Workshop
%D 2026
%8 October
%I Association for Computational Linguistics
%C Budapest, Hungary
%@ 979-8-89176-481-1
%F charalampous-djouvas-2026-createdebate
%X We introduce the CreateDebate Arguments Dataset, a large-scale, unfiltered collection of 383,220 arguments from 7,435 of the most active for/against debates on the CreateDebate online debate platform, spanning 16 years of activity. Unlike existing computational argumentation resources, the dataset combines large scale with hierarchical debate-tree structure, author-assigned stance labels, community vote scores, and relational tags that explicitly mark when one argument disputes another. Because the full dataset is unfiltered, we release it under a gated access agreement and additionally release an openly available, manually curated subset of 84,872 arguments from 578 debates. To demonstrate the dataset’s utility, we define two counter-argument retrieval benchmarks on the curated subset: a targeted setting that uses the dispute tag as author-verified ground truth, and a general setting in which any opposing-side argument is a valid counter. Evaluating a BM25 baseline, a frozen bi-encoder, and a fine-tuned bi-encoder, we find consistent but bounded gains from fine-tuning on disputed pairs, a negative effect of debate-level context on within-debate retrieval, and limited cross-task transfer between the targeted and general settings. A qualitative analysis surfaces failure modes specific to naturally occurring debate. The dataset and models are released to the community.
%U https://aclanthology.org/2026.wac-1.2/
%P 8-21
Markdown (Informal)
[The CreateDebate Arguments Dataset: A Large-Scale Naturalistic Corpus for Computational Argumentation](https://aclanthology.org/2026.wac-1.2/) (Charalampous & Djouvas, WAC 2026)
ACL