@inproceedings{li-etal-2024-lmeme,
title = "{LMEME} at {S}em{E}val-2024 Task 4: Teacher Student Fusion - Integrating {CLIP} with {LLM}s for Enhanced Persuasion Detection",
author = "Li, Shiyi and
Wang, Yike and
Yang, Liang and
Zhang, Shaowu and
Lin, Hongfei",
editor = {Ojha, Atul Kr. and
Do{\u{g}}ru{\"o}z, A. Seza and
Tayyar Madabushi, Harish and
Da San Martino, Giovanni and
Rosenthal, Sara and
Ros{\'a}, Aiala},
booktitle = "Proceedings of the 18th International Workshop on Semantic Evaluation (SemEval-2024)",
month = jun,
year = "2024",
address = "Mexico City, Mexico",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2024.semeval-1.92",
doi = "10.18653/v1/2024.semeval-1.92",
pages = "628--633",
abstract = "This paper describes our system used in the SemEval-2024 Task 4 Multilingual Detection of Persuasion Techniques in Memes. Our team proposes a detection system that employs a Teacher Student Fusion framework. Initially, a Large Language Model serves as the teacher, engaging in abductive reasoning on multimodal inputs to generate background knowledge on persuasion techniques, assisting in the training of a smaller downstream model. The student model adopts CLIP as an encoder for text and image features, and we incorporate an attention mechanism for modality alignment. Ultimately, our proposed system achieves a Macro-F1 score of 0.8103, ranking 1st out of 20 on the leaderboard of Subtask 2b in English. In Bulgarian, Macedonian and Arabic, our detection capabilities are ranked 1/15, 3/15 and 14/15.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="li-etal-2024-lmeme">
<titleInfo>
<title>LMEME at SemEval-2024 Task 4: Teacher Student Fusion - Integrating CLIP with LLMs for Enhanced Persuasion Detection</title>
</titleInfo>
<name type="personal">
<namePart type="given">Shiyi</namePart>
<namePart type="family">Li</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yike</namePart>
<namePart type="family">Wang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Liang</namePart>
<namePart type="family">Yang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Shaowu</namePart>
<namePart type="family">Zhang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hongfei</namePart>
<namePart type="family">Lin</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2024-06</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 18th International Workshop on Semantic Evaluation (SemEval-2024)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Atul</namePart>
<namePart type="given">Kr.</namePart>
<namePart type="family">Ojha</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">A</namePart>
<namePart type="given">Seza</namePart>
<namePart type="family">Doğruöz</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Harish</namePart>
<namePart type="family">Tayyar Madabushi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Giovanni</namePart>
<namePart type="family">Da San Martino</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sara</namePart>
<namePart type="family">Rosenthal</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Aiala</namePart>
<namePart type="family">Rosá</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Mexico City, Mexico</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>This paper describes our system used in the SemEval-2024 Task 4 Multilingual Detection of Persuasion Techniques in Memes. Our team proposes a detection system that employs a Teacher Student Fusion framework. Initially, a Large Language Model serves as the teacher, engaging in abductive reasoning on multimodal inputs to generate background knowledge on persuasion techniques, assisting in the training of a smaller downstream model. The student model adopts CLIP as an encoder for text and image features, and we incorporate an attention mechanism for modality alignment. Ultimately, our proposed system achieves a Macro-F1 score of 0.8103, ranking 1st out of 20 on the leaderboard of Subtask 2b in English. In Bulgarian, Macedonian and Arabic, our detection capabilities are ranked 1/15, 3/15 and 14/15.</abstract>
<identifier type="citekey">li-etal-2024-lmeme</identifier>
<identifier type="doi">10.18653/v1/2024.semeval-1.92</identifier>
<location>
<url>https://aclanthology.org/2024.semeval-1.92</url>
</location>
<part>
<date>2024-06</date>
<extent unit="page">
<start>628</start>
<end>633</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T LMEME at SemEval-2024 Task 4: Teacher Student Fusion - Integrating CLIP with LLMs for Enhanced Persuasion Detection
%A Li, Shiyi
%A Wang, Yike
%A Yang, Liang
%A Zhang, Shaowu
%A Lin, Hongfei
%Y Ojha, Atul Kr.
%Y Doğruöz, A. Seza
%Y Tayyar Madabushi, Harish
%Y Da San Martino, Giovanni
%Y Rosenthal, Sara
%Y Rosá, Aiala
%S Proceedings of the 18th International Workshop on Semantic Evaluation (SemEval-2024)
%D 2024
%8 June
%I Association for Computational Linguistics
%C Mexico City, Mexico
%F li-etal-2024-lmeme
%X This paper describes our system used in the SemEval-2024 Task 4 Multilingual Detection of Persuasion Techniques in Memes. Our team proposes a detection system that employs a Teacher Student Fusion framework. Initially, a Large Language Model serves as the teacher, engaging in abductive reasoning on multimodal inputs to generate background knowledge on persuasion techniques, assisting in the training of a smaller downstream model. The student model adopts CLIP as an encoder for text and image features, and we incorporate an attention mechanism for modality alignment. Ultimately, our proposed system achieves a Macro-F1 score of 0.8103, ranking 1st out of 20 on the leaderboard of Subtask 2b in English. In Bulgarian, Macedonian and Arabic, our detection capabilities are ranked 1/15, 3/15 and 14/15.
%R 10.18653/v1/2024.semeval-1.92
%U https://aclanthology.org/2024.semeval-1.92
%U https://doi.org/10.18653/v1/2024.semeval-1.92
%P 628-633
Markdown (Informal)
[LMEME at SemEval-2024 Task 4: Teacher Student Fusion - Integrating CLIP with LLMs for Enhanced Persuasion Detection](https://aclanthology.org/2024.semeval-1.92) (Li et al., SemEval 2024)
ACL