@inproceedings{kohita-yoshioka-2026-memes,
title = "Memes-as-Replies: Can Models Select Humorous Manga Panel Responses?",
author = "Kohita, Ryosuke and
Yoshioka, Seiichiro",
editor = "Lee, Hung-Yi and
Dev, Sunipa and
Li, Jessy and
Elliott, Desmond",
booktitle = "Findings of the {A}ssociation for {C}omputational {L}inguistics: {EMNLP} 2026",
month = oct,
year = "2026",
address = "Budapest, Hungary",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2026.findings-emnlp.2076/",
doi = "10.18653/2026.findings-emnlp.2076",
pages = "44207--44222",
ISBN = "979-8-89176-462-0",
abstract = "Memes are widely used not only as static artifacts but also as interactive replies in online conversations. While computational research has focused on analyzing intrinsic properties of memes, the dynamic and contextual use of memes to create humor remains largely unaddressed. We introduce the Meme Reply Selection task and present MaMe-Re, a benchmark of 100,000 human-annotated context{--}meme pairs built from openly licensed Japanese manga panels. Our analysis reveals three key findings: (1) large language models show modest advantages over embedding methods by capturing social cues such as irony and exaggeration beyond surface-level semantic matching; (2) visual information does not improve performance, revealing a gap between understanding visual content and effectively using it for contextual humor; (3) while models can match human judgments when the humorous option is clearly distinguishable, they struggle to distinguish subtle differences in wit among semantically similar candidates. These findings establish contextually humorous reply selection as an open challenge for current models."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="kohita-yoshioka-2026-memes">
<titleInfo>
<title>Memes-as-Replies: Can Models Select Humorous Manga Panel Responses?</title>
</titleInfo>
<name type="personal">
<namePart type="given">Ryosuke</namePart>
<namePart type="family">Kohita</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Seiichiro</namePart>
<namePart type="family">Yoshioka</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>Findings of the Association for Computational Linguistics: EMNLP 2026</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">979-8-89176-462-0</identifier>
</relatedItem>
<abstract>Memes are widely used not only as static artifacts but also as interactive replies in online conversations. While computational research has focused on analyzing intrinsic properties of memes, the dynamic and contextual use of memes to create humor remains largely unaddressed. We introduce the Meme Reply Selection task and present MaMe-Re, a benchmark of 100,000 human-annotated context–meme pairs built from openly licensed Japanese manga panels. Our analysis reveals three key findings: (1) large language models show modest advantages over embedding methods by capturing social cues such as irony and exaggeration beyond surface-level semantic matching; (2) visual information does not improve performance, revealing a gap between understanding visual content and effectively using it for contextual humor; (3) while models can match human judgments when the humorous option is clearly distinguishable, they struggle to distinguish subtle differences in wit among semantically similar candidates. These findings establish contextually humorous reply selection as an open challenge for current models.</abstract>
<identifier type="citekey">kohita-yoshioka-2026-memes</identifier>
<identifier type="doi">10.18653/2026.findings-emnlp.2076</identifier>
<location>
<url>https://aclanthology.org/2026.findings-emnlp.2076/</url>
</location>
<part>
<date>2026-10</date>
<extent unit="page">
<start>44207</start>
<end>44222</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Memes-as-Replies: Can Models Select Humorous Manga Panel Responses?
%A Kohita, Ryosuke
%A Yoshioka, Seiichiro
%Y Lee, Hung-Yi
%Y Dev, Sunipa
%Y Li, Jessy
%Y Elliott, Desmond
%S Findings of the Association for Computational Linguistics: EMNLP 2026
%D 2026
%8 October
%I Association for Computational Linguistics
%C Budapest, Hungary
%@ 979-8-89176-462-0
%F kohita-yoshioka-2026-memes
%X Memes are widely used not only as static artifacts but also as interactive replies in online conversations. While computational research has focused on analyzing intrinsic properties of memes, the dynamic and contextual use of memes to create humor remains largely unaddressed. We introduce the Meme Reply Selection task and present MaMe-Re, a benchmark of 100,000 human-annotated context–meme pairs built from openly licensed Japanese manga panels. Our analysis reveals three key findings: (1) large language models show modest advantages over embedding methods by capturing social cues such as irony and exaggeration beyond surface-level semantic matching; (2) visual information does not improve performance, revealing a gap between understanding visual content and effectively using it for contextual humor; (3) while models can match human judgments when the humorous option is clearly distinguishable, they struggle to distinguish subtle differences in wit among semantically similar candidates. These findings establish contextually humorous reply selection as an open challenge for current models.
%R 10.18653/2026.findings-emnlp.2076
%U https://aclanthology.org/2026.findings-emnlp.2076/
%U https://doi.org/10.18653/2026.findings-emnlp.2076
%P 44207-44222
Markdown (Informal)
[Memes-as-Replies: Can Models Select Humorous Manga Panel Responses?](https://aclanthology.org/2026.findings-emnlp.2076/) (Kohita & Yoshioka, Findings 2026)
ACL