@inproceedings{grecu-cocarascu-2026-topic,
title = "Topic-Guided Prompting for Argument Stance Classification",
author = "Grecu, Bogdan and
Cocarascu, Oana",
editor = "Elaraby, Mohamed and
Hautli-Janisz, Annette and
Romberg, Julia and
Musi, Elena and
Ruggeri, Federico and
Lawrence, John",
booktitle = "Proceedings of the 13th Workshop on Argument Mining and Reasoning",
month = jul,
year = "2026",
address = "San Diego, California, USA",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2026.argmining-1.4/",
pages = "32--36",
ISBN = "979-8-89176-399-9",
abstract = "Stance classification is a core task in argument mining and subjectivity analysis, crucial for understanding public discourse and opinion dynamics on social media. Despite their impressive few-shot capabilities, Large Language Models (LLMs) remain sensitive to prompt construction, including the selection and ordering of in-context examples. In this paper, we propose a Topic-Guided prompting method for argument stance classification that dynamically integrates topic-specific information into the few-shot context. We evaluate our method on five LLMs across three datasets spanning formal debates and user-generated online comments. Our extensive evaluation shows that our proposed Topic-Guided prompting outperforms standard few-shot prompting and state-of-the-art example selection strategies. Further analysis indicates that our method reduces the bias towards the `support' class observed in several models, resulting in more balanced predictions across stances and thus a more robust approach to stance classification."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="grecu-cocarascu-2026-topic">
<titleInfo>
<title>Topic-Guided Prompting for Argument Stance Classification</title>
</titleInfo>
<name type="personal">
<namePart type="given">Bogdan</namePart>
<namePart type="family">Grecu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Oana</namePart>
<namePart type="family">Cocarascu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2026-07</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 13th Workshop on Argument Mining and Reasoning</title>
</titleInfo>
<name type="personal">
<namePart type="given">Mohamed</namePart>
<namePart type="family">Elaraby</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Annette</namePart>
<namePart type="family">Hautli-Janisz</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Julia</namePart>
<namePart type="family">Romberg</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Elena</namePart>
<namePart type="family">Musi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Federico</namePart>
<namePart type="family">Ruggeri</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">John</namePart>
<namePart type="family">Lawrence</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">San Diego, California, USA</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-8-89176-399-9</identifier>
</relatedItem>
<abstract>Stance classification is a core task in argument mining and subjectivity analysis, crucial for understanding public discourse and opinion dynamics on social media. Despite their impressive few-shot capabilities, Large Language Models (LLMs) remain sensitive to prompt construction, including the selection and ordering of in-context examples. In this paper, we propose a Topic-Guided prompting method for argument stance classification that dynamically integrates topic-specific information into the few-shot context. We evaluate our method on five LLMs across three datasets spanning formal debates and user-generated online comments. Our extensive evaluation shows that our proposed Topic-Guided prompting outperforms standard few-shot prompting and state-of-the-art example selection strategies. Further analysis indicates that our method reduces the bias towards the ‘support’ class observed in several models, resulting in more balanced predictions across stances and thus a more robust approach to stance classification.</abstract>
<identifier type="citekey">grecu-cocarascu-2026-topic</identifier>
<location>
<url>https://aclanthology.org/2026.argmining-1.4/</url>
</location>
<part>
<date>2026-07</date>
<extent unit="page">
<start>32</start>
<end>36</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Topic-Guided Prompting for Argument Stance Classification
%A Grecu, Bogdan
%A Cocarascu, Oana
%Y Elaraby, Mohamed
%Y Hautli-Janisz, Annette
%Y Romberg, Julia
%Y Musi, Elena
%Y Ruggeri, Federico
%Y Lawrence, John
%S Proceedings of the 13th Workshop on Argument Mining and Reasoning
%D 2026
%8 July
%I Association for Computational Linguistics
%C San Diego, California, USA
%@ 979-8-89176-399-9
%F grecu-cocarascu-2026-topic
%X Stance classification is a core task in argument mining and subjectivity analysis, crucial for understanding public discourse and opinion dynamics on social media. Despite their impressive few-shot capabilities, Large Language Models (LLMs) remain sensitive to prompt construction, including the selection and ordering of in-context examples. In this paper, we propose a Topic-Guided prompting method for argument stance classification that dynamically integrates topic-specific information into the few-shot context. We evaluate our method on five LLMs across three datasets spanning formal debates and user-generated online comments. Our extensive evaluation shows that our proposed Topic-Guided prompting outperforms standard few-shot prompting and state-of-the-art example selection strategies. Further analysis indicates that our method reduces the bias towards the ‘support’ class observed in several models, resulting in more balanced predictions across stances and thus a more robust approach to stance classification.
%U https://aclanthology.org/2026.argmining-1.4/
%P 32-36
Markdown (Informal)
[Topic-Guided Prompting for Argument Stance Classification](https://aclanthology.org/2026.argmining-1.4/) (Grecu & Cocarascu, ArgMining 2026)
ACL