@inproceedings{zhang-etal-2024-somelvlm,
title = "{S}o{M}e{LVLM}: A Large Vision Language Model for Social Media Processing",
author = "Zhang, Xinnong and
Kuang, Haoyu and
Mou, Xinyi and
Lyu, Hanjia and
Wu, Kun and
Chen, Siming and
Luo, Jiebo and
Huang, Xuanjing and
Wei, Zhongyu",
editor = "Ku, Lun-Wei and
Martins, Andre and
Srikumar, Vivek",
booktitle = "Findings of the Association for Computational Linguistics: ACL 2024",
month = aug,
year = "2024",
address = "Bangkok, Thailand",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2024.findings-acl.140/",
doi = "10.18653/v1/2024.findings-acl.140",
pages = "2366--2389",
abstract = "The growth of social media, characterized by its multimodal nature, has led to the emergence of diverse phenomena and challenges, which calls for an effective approach to uniformly solve automated tasks. The powerful Large Vision Language Models make it possible to handle a variety of tasks simultaneously, but even with carefully designed prompting methods, the general domain models often fall short in aligning with the unique speaking style and context of social media tasks. In this paper, we introduce a Large Vision Language Model for Social Media Processing (SoMeLVLM), which is a cognitive framework equipped with five key capabilities including knowledge {\&} comprehension, application, analysis, evaluation, and creation. SoMeLVLM is designed to understand and generate realistic social media behavior. We have developed a 654k multimodal social media instruction-tuning dataset to support our cognitive framework and fine-tune our model. Our experiments demonstrate that SoMeLVLM achieves state-of-the-art performance in multiple social media tasks. Further analysis shows its significant advantages over baselines in terms of cognitive abilities."
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="zhang-etal-2024-somelvlm">
<titleInfo>
<title>SoMeLVLM: A Large Vision Language Model for Social Media Processing</title>
</titleInfo>
<name type="personal">
<namePart type="given">Xinnong</namePart>
<namePart type="family">Zhang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Haoyu</namePart>
<namePart type="family">Kuang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Xinyi</namePart>
<namePart type="family">Mou</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hanjia</namePart>
<namePart type="family">Lyu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Kun</namePart>
<namePart type="family">Wu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Siming</namePart>
<namePart type="family">Chen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jiebo</namePart>
<namePart type="family">Luo</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Xuanjing</namePart>
<namePart type="family">Huang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Zhongyu</namePart>
<namePart type="family">Wei</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2024-08</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Findings of the Association for Computational Linguistics: ACL 2024</title>
</titleInfo>
<name type="personal">
<namePart type="given">Lun-Wei</namePart>
<namePart type="family">Ku</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Andre</namePart>
<namePart type="family">Martins</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Vivek</namePart>
<namePart type="family">Srikumar</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Bangkok, Thailand</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>The growth of social media, characterized by its multimodal nature, has led to the emergence of diverse phenomena and challenges, which calls for an effective approach to uniformly solve automated tasks. The powerful Large Vision Language Models make it possible to handle a variety of tasks simultaneously, but even with carefully designed prompting methods, the general domain models often fall short in aligning with the unique speaking style and context of social media tasks. In this paper, we introduce a Large Vision Language Model for Social Media Processing (SoMeLVLM), which is a cognitive framework equipped with five key capabilities including knowledge & comprehension, application, analysis, evaluation, and creation. SoMeLVLM is designed to understand and generate realistic social media behavior. We have developed a 654k multimodal social media instruction-tuning dataset to support our cognitive framework and fine-tune our model. Our experiments demonstrate that SoMeLVLM achieves state-of-the-art performance in multiple social media tasks. Further analysis shows its significant advantages over baselines in terms of cognitive abilities.</abstract>
<identifier type="citekey">zhang-etal-2024-somelvlm</identifier>
<identifier type="doi">10.18653/v1/2024.findings-acl.140</identifier>
<location>
<url>https://aclanthology.org/2024.findings-acl.140/</url>
</location>
<part>
<date>2024-08</date>
<extent unit="page">
<start>2366</start>
<end>2389</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T SoMeLVLM: A Large Vision Language Model for Social Media Processing
%A Zhang, Xinnong
%A Kuang, Haoyu
%A Mou, Xinyi
%A Lyu, Hanjia
%A Wu, Kun
%A Chen, Siming
%A Luo, Jiebo
%A Huang, Xuanjing
%A Wei, Zhongyu
%Y Ku, Lun-Wei
%Y Martins, Andre
%Y Srikumar, Vivek
%S Findings of the Association for Computational Linguistics: ACL 2024
%D 2024
%8 August
%I Association for Computational Linguistics
%C Bangkok, Thailand
%F zhang-etal-2024-somelvlm
%X The growth of social media, characterized by its multimodal nature, has led to the emergence of diverse phenomena and challenges, which calls for an effective approach to uniformly solve automated tasks. The powerful Large Vision Language Models make it possible to handle a variety of tasks simultaneously, but even with carefully designed prompting methods, the general domain models often fall short in aligning with the unique speaking style and context of social media tasks. In this paper, we introduce a Large Vision Language Model for Social Media Processing (SoMeLVLM), which is a cognitive framework equipped with five key capabilities including knowledge & comprehension, application, analysis, evaluation, and creation. SoMeLVLM is designed to understand and generate realistic social media behavior. We have developed a 654k multimodal social media instruction-tuning dataset to support our cognitive framework and fine-tune our model. Our experiments demonstrate that SoMeLVLM achieves state-of-the-art performance in multiple social media tasks. Further analysis shows its significant advantages over baselines in terms of cognitive abilities.
%R 10.18653/v1/2024.findings-acl.140
%U https://aclanthology.org/2024.findings-acl.140/
%U https://doi.org/10.18653/v1/2024.findings-acl.140
%P 2366-2389
Markdown (Informal)
[SoMeLVLM: A Large Vision Language Model for Social Media Processing](https://aclanthology.org/2024.findings-acl.140/) (Zhang et al., Findings 2024)
ACL
- Xinnong Zhang, Haoyu Kuang, Xinyi Mou, Hanjia Lyu, Kun Wu, Siming Chen, Jiebo Luo, Xuanjing Huang, and Zhongyu Wei. 2024. SoMeLVLM: A Large Vision Language Model for Social Media Processing. In Findings of the Association for Computational Linguistics: ACL 2024, pages 2366–2389, Bangkok, Thailand. Association for Computational Linguistics.