@inproceedings{nguyen-etal-2026-memeargs,
title = "{M}eme{A}rgs: Vision-Language Argument Mining in Persuasive Memes",
author = "Nguyen, Khoi P. N. and
Nguyen, Trung N. and
Li, Terrence and
Patel, Teerth and
Ng, Vincent",
editor = "Lee, Hung-Yi and
Dev, Sunipa and
Li, Jessy and
Elliott, Desmond",
booktitle = "Proceedings of the 2026 Conference on Empirical Methods in Natural Language Processing",
month = oct,
year = "2026",
address = "Budapest, Hungary",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2026.emnlp-main.2361/",
pages = "53619--53642",
ISBN = "979-8-89176-459-0",
abstract = "On today{'}s social media, many argumentative artifacts appear in mixed image-text format. Meanwhile, the argument mining community has seen much success in developing argument understanding technologies in text. In this work, we bridge that gap by studying vision-language argument (VLA) parsing: generating an argument graph that captures both the explicit and implicit components of a vision-language argument. To lay the groundwork for this task, we annotate MemeArgs, a corpus of argument graphs for 614 persuasive memes. We then propose an automatic evaluation protocol for VLA parsing that accommodates its generative nature and follows standard argument mining practice. Evaluating current general-purpose vision-language models, we found that they all failed to perform knowledge-grounded visual perception reliably, which distorts their understanding of the arguments. VLA parsing thus presents an exciting challenge for multimodal argument understanding."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="nguyen-etal-2026-memeargs">
<titleInfo>
<title>MemeArgs: Vision-Language Argument Mining in Persuasive Memes</title>
</titleInfo>
<name type="personal">
<namePart type="given">Khoi</namePart>
<namePart type="given">P</namePart>
<namePart type="given">N</namePart>
<namePart type="family">Nguyen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Trung</namePart>
<namePart type="given">N</namePart>
<namePart type="family">Nguyen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Terrence</namePart>
<namePart type="family">Li</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Teerth</namePart>
<namePart type="family">Patel</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Vincent</namePart>
<namePart type="family">Ng</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 2026 Conference on Empirical Methods in Natural Language Processing</title>
</titleInfo>
<name type="personal">
<namePart type="given">Hung-Yi</namePart>
<namePart type="family">Lee</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sunipa</namePart>
<namePart type="family">Dev</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jessy</namePart>
<namePart type="family">Li</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Desmond</namePart>
<namePart type="family">Elliott</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">979-8-89176-459-0</identifier>
</relatedItem>
<abstract>On today’s social media, many argumentative artifacts appear in mixed image-text format. Meanwhile, the argument mining community has seen much success in developing argument understanding technologies in text. In this work, we bridge that gap by studying vision-language argument (VLA) parsing: generating an argument graph that captures both the explicit and implicit components of a vision-language argument. To lay the groundwork for this task, we annotate MemeArgs, a corpus of argument graphs for 614 persuasive memes. We then propose an automatic evaluation protocol for VLA parsing that accommodates its generative nature and follows standard argument mining practice. Evaluating current general-purpose vision-language models, we found that they all failed to perform knowledge-grounded visual perception reliably, which distorts their understanding of the arguments. VLA parsing thus presents an exciting challenge for multimodal argument understanding.</abstract>
<identifier type="citekey">nguyen-etal-2026-memeargs</identifier>
<location>
<url>https://aclanthology.org/2026.emnlp-main.2361/</url>
</location>
<part>
<date>2026-10</date>
<extent unit="page">
<start>53619</start>
<end>53642</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T MemeArgs: Vision-Language Argument Mining in Persuasive Memes
%A Nguyen, Khoi P. N.
%A Nguyen, Trung N.
%A Li, Terrence
%A Patel, Teerth
%A Ng, Vincent
%Y Lee, Hung-Yi
%Y Dev, Sunipa
%Y Li, Jessy
%Y Elliott, Desmond
%S Proceedings of the 2026 Conference on Empirical Methods in Natural Language Processing
%D 2026
%8 October
%I Association for Computational Linguistics
%C Budapest, Hungary
%@ 979-8-89176-459-0
%F nguyen-etal-2026-memeargs
%X On today’s social media, many argumentative artifacts appear in mixed image-text format. Meanwhile, the argument mining community has seen much success in developing argument understanding technologies in text. In this work, we bridge that gap by studying vision-language argument (VLA) parsing: generating an argument graph that captures both the explicit and implicit components of a vision-language argument. To lay the groundwork for this task, we annotate MemeArgs, a corpus of argument graphs for 614 persuasive memes. We then propose an automatic evaluation protocol for VLA parsing that accommodates its generative nature and follows standard argument mining practice. Evaluating current general-purpose vision-language models, we found that they all failed to perform knowledge-grounded visual perception reliably, which distorts their understanding of the arguments. VLA parsing thus presents an exciting challenge for multimodal argument understanding.
%U https://aclanthology.org/2026.emnlp-main.2361/
%P 53619-53642
Markdown (Informal)
[MemeArgs: Vision-Language Argument Mining in Persuasive Memes](https://aclanthology.org/2026.emnlp-main.2361/) (Nguyen et al., EMNLP 2026)
ACL
- Khoi P. N. Nguyen, Trung N. Nguyen, Terrence Li, Teerth Patel, and Vincent Ng. 2026. MemeArgs: Vision-Language Argument Mining in Persuasive Memes. In Proceedings of the 2026 Conference on Empirical Methods in Natural Language Processing, pages 53619–53642, Budapest, Hungary. Association for Computational Linguistics.