@inproceedings{de-giorgis-etal-2026-quest,
title = "{M}-{QUEST} - Meme Question-Understanding Evaluation on Semantics and Toxicity",
author = "De Giorgis, Stefano and
Chen, Ting-Chih and
Ilievski, Filip",
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.164/",
pages = "3759--3784",
ISBN = "979-8-89176-459-0",
abstract = "Internet memes are a powerful form of online communication, yet their multimodal nature and reliance on commonsense and cultural knowledge make automated toxicity detection challenging. Prior work has studied individual dimensions of memes: textual content via optical character recognition, visual content via object recognition, and toxicity via hate speech detection, but lacks a unified architecture that formally identifies the semantic dimensions contributing to meme toxicity. We present three contributions: (1) a semantic framework identifying the dimensions necessary for meme interpretation; (2) a corresponding benchmark, M-QUEST, of 609 question-answer pairs for 307 memes, generated via a semi-automatic process grounded in the framework; and (3) an empirical evaluation of 12 VLMs on M-QUEST. The results show that the instruction-tuned models with reasoning capabilities significantly outperform others, whereas pragmatic inference remains challenging across all models."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="de-giorgis-etal-2026-quest">
<titleInfo>
<title>M-QUEST - Meme Question-Understanding Evaluation on Semantics and Toxicity</title>
</titleInfo>
<name type="personal">
<namePart type="given">Stefano</namePart>
<namePart type="family">De Giorgis</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ting-Chih</namePart>
<namePart type="family">Chen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Filip</namePart>
<namePart type="family">Ilievski</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>Internet memes are a powerful form of online communication, yet their multimodal nature and reliance on commonsense and cultural knowledge make automated toxicity detection challenging. Prior work has studied individual dimensions of memes: textual content via optical character recognition, visual content via object recognition, and toxicity via hate speech detection, but lacks a unified architecture that formally identifies the semantic dimensions contributing to meme toxicity. We present three contributions: (1) a semantic framework identifying the dimensions necessary for meme interpretation; (2) a corresponding benchmark, M-QUEST, of 609 question-answer pairs for 307 memes, generated via a semi-automatic process grounded in the framework; and (3) an empirical evaluation of 12 VLMs on M-QUEST. The results show that the instruction-tuned models with reasoning capabilities significantly outperform others, whereas pragmatic inference remains challenging across all models.</abstract>
<identifier type="citekey">de-giorgis-etal-2026-quest</identifier>
<location>
<url>https://aclanthology.org/2026.emnlp-main.164/</url>
</location>
<part>
<date>2026-10</date>
<extent unit="page">
<start>3759</start>
<end>3784</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T M-QUEST - Meme Question-Understanding Evaluation on Semantics and Toxicity
%A De Giorgis, Stefano
%A Chen, Ting-Chih
%A Ilievski, Filip
%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 de-giorgis-etal-2026-quest
%X Internet memes are a powerful form of online communication, yet their multimodal nature and reliance on commonsense and cultural knowledge make automated toxicity detection challenging. Prior work has studied individual dimensions of memes: textual content via optical character recognition, visual content via object recognition, and toxicity via hate speech detection, but lacks a unified architecture that formally identifies the semantic dimensions contributing to meme toxicity. We present three contributions: (1) a semantic framework identifying the dimensions necessary for meme interpretation; (2) a corresponding benchmark, M-QUEST, of 609 question-answer pairs for 307 memes, generated via a semi-automatic process grounded in the framework; and (3) an empirical evaluation of 12 VLMs on M-QUEST. The results show that the instruction-tuned models with reasoning capabilities significantly outperform others, whereas pragmatic inference remains challenging across all models.
%U https://aclanthology.org/2026.emnlp-main.164/
%P 3759-3784
Markdown (Informal)
[M-QUEST - Meme Question-Understanding Evaluation on Semantics and Toxicity](https://aclanthology.org/2026.emnlp-main.164/) (De Giorgis et al., EMNLP 2026)
ACL