@inproceedings{liu-yao-2026-tool,
title = "Tool-meme: Tool-Learning Framework for Multimodal Meme Detection",
author = "Liu, Shuai and
Yao, Yingying",
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.676/",
doi = "10.18653/2026.findings-emnlp.676",
pages = "14192--14215",
ISBN = "979-8-89176-462-0",
abstract = "With the explosive growth of social media, multimodal memes (text and images) have become a key carrier of misinformation dissemination and emotional manipulation because they strongly depend on cultural background, satirical metaphor, and current events. Existing detection methods mostly rely on end-to-end deep learning models, but they face two fundamental limitations: first, static models are difficult to capture the dynamic semantic evolution of memes; second, fixed architectures cannot adapt to meme heterogeneity. This work proposes a Tool-Learning Framework for Multimodal Meme Detection (Tool-meme), a Large Multimodal Model (LMM)-driven tools-learning framework. The framework uses multimodal representations only as input features, dynamically orchestrates tool chains through retrieval-augmented generation and meta-cognitive planning, and uses reinforcement learning to maximize tool-use efficiency. On HarM, FHM, and MAMI, Tool-meme outperforms all evaluated direct-LMM and agentic baselines under frozen-executor setting. Additional transfer and deployment analyses show consistent gains across tested executor families while lowering tool calls and cost vs. exhaustive execution, with explicit evidence chains for inspection."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="liu-yao-2026-tool">
<titleInfo>
<title>Tool-meme: Tool-Learning Framework for Multimodal Meme Detection</title>
</titleInfo>
<name type="personal">
<namePart type="given">Shuai</namePart>
<namePart type="family">Liu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yingying</namePart>
<namePart type="family">Yao</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>With the explosive growth of social media, multimodal memes (text and images) have become a key carrier of misinformation dissemination and emotional manipulation because they strongly depend on cultural background, satirical metaphor, and current events. Existing detection methods mostly rely on end-to-end deep learning models, but they face two fundamental limitations: first, static models are difficult to capture the dynamic semantic evolution of memes; second, fixed architectures cannot adapt to meme heterogeneity. This work proposes a Tool-Learning Framework for Multimodal Meme Detection (Tool-meme), a Large Multimodal Model (LMM)-driven tools-learning framework. The framework uses multimodal representations only as input features, dynamically orchestrates tool chains through retrieval-augmented generation and meta-cognitive planning, and uses reinforcement learning to maximize tool-use efficiency. On HarM, FHM, and MAMI, Tool-meme outperforms all evaluated direct-LMM and agentic baselines under frozen-executor setting. Additional transfer and deployment analyses show consistent gains across tested executor families while lowering tool calls and cost vs. exhaustive execution, with explicit evidence chains for inspection.</abstract>
<identifier type="citekey">liu-yao-2026-tool</identifier>
<identifier type="doi">10.18653/2026.findings-emnlp.676</identifier>
<location>
<url>https://aclanthology.org/2026.findings-emnlp.676/</url>
</location>
<part>
<date>2026-10</date>
<extent unit="page">
<start>14192</start>
<end>14215</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Tool-meme: Tool-Learning Framework for Multimodal Meme Detection
%A Liu, Shuai
%A Yao, Yingying
%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 liu-yao-2026-tool
%X With the explosive growth of social media, multimodal memes (text and images) have become a key carrier of misinformation dissemination and emotional manipulation because they strongly depend on cultural background, satirical metaphor, and current events. Existing detection methods mostly rely on end-to-end deep learning models, but they face two fundamental limitations: first, static models are difficult to capture the dynamic semantic evolution of memes; second, fixed architectures cannot adapt to meme heterogeneity. This work proposes a Tool-Learning Framework for Multimodal Meme Detection (Tool-meme), a Large Multimodal Model (LMM)-driven tools-learning framework. The framework uses multimodal representations only as input features, dynamically orchestrates tool chains through retrieval-augmented generation and meta-cognitive planning, and uses reinforcement learning to maximize tool-use efficiency. On HarM, FHM, and MAMI, Tool-meme outperforms all evaluated direct-LMM and agentic baselines under frozen-executor setting. Additional transfer and deployment analyses show consistent gains across tested executor families while lowering tool calls and cost vs. exhaustive execution, with explicit evidence chains for inspection.
%R 10.18653/2026.findings-emnlp.676
%U https://aclanthology.org/2026.findings-emnlp.676/
%U https://doi.org/10.18653/2026.findings-emnlp.676
%P 14192-14215
Markdown (Informal)
[Tool-meme: Tool-Learning Framework for Multimodal Meme Detection](https://aclanthology.org/2026.findings-emnlp.676/) (Liu & Yao, Findings 2026)
ACL