@inproceedings{lee-etal-2024-large,
title = "Large Language Models can Share Images, Too!",
author = "Lee, Young-Jun and
Lee, Dokyong and
Sung, Joo Won and
Hyeon, Jonghwan and
Choi, Ho-Jin",
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.39/",
doi = "10.18653/v1/2024.findings-acl.39",
pages = "692--713",
abstract = "This paper explores the image-sharing capability of Large Language Models (LLMs), such as GPT-4 and LLaMA 2, in a zero-shot setting. To facilitate a comprehensive evaluation of LLMs, we introduce the photochatplus dataset, which includes enriched annotations (ie intent, triggering sentence, image description, and salient information). Furthermore, we present the gradient-free and extensible Decide, Describe, and Retrieve () framework. With extensive experiments, we unlock the image-sharing capability of equipped with LLMs in zero-shot prompting, with ChatGPT achieving the best performance.Our findings also reveal the emergent image-sharing ability in LLMs under zero-shot conditions, validating the effectiveness of . We use this framework to demonstrate its practicality and effectiveness in two real-world scenarios: (1) human-bot interaction and (2) dataset augmentation. To the best of our knowledge, this is the first study to assess the image-sharing ability of various LLMs in a zero-shot setting. We make our source code and dataset publicly available at https://github.com/passing2961/DribeR."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="lee-etal-2024-large">
<titleInfo>
<title>Large Language Models can Share Images, Too!</title>
</titleInfo>
<name type="personal">
<namePart type="given">Young-Jun</namePart>
<namePart type="family">Lee</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Dokyong</namePart>
<namePart type="family">Lee</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Joo</namePart>
<namePart type="given">Won</namePart>
<namePart type="family">Sung</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jonghwan</namePart>
<namePart type="family">Hyeon</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ho-Jin</namePart>
<namePart type="family">Choi</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>This paper explores the image-sharing capability of Large Language Models (LLMs), such as GPT-4 and LLaMA 2, in a zero-shot setting. To facilitate a comprehensive evaluation of LLMs, we introduce the photochatplus dataset, which includes enriched annotations (ie intent, triggering sentence, image description, and salient information). Furthermore, we present the gradient-free and extensible Decide, Describe, and Retrieve () framework. With extensive experiments, we unlock the image-sharing capability of equipped with LLMs in zero-shot prompting, with ChatGPT achieving the best performance.Our findings also reveal the emergent image-sharing ability in LLMs under zero-shot conditions, validating the effectiveness of . We use this framework to demonstrate its practicality and effectiveness in two real-world scenarios: (1) human-bot interaction and (2) dataset augmentation. To the best of our knowledge, this is the first study to assess the image-sharing ability of various LLMs in a zero-shot setting. We make our source code and dataset publicly available at https://github.com/passing2961/DribeR.</abstract>
<identifier type="citekey">lee-etal-2024-large</identifier>
<identifier type="doi">10.18653/v1/2024.findings-acl.39</identifier>
<location>
<url>https://aclanthology.org/2024.findings-acl.39/</url>
</location>
<part>
<date>2024-08</date>
<extent unit="page">
<start>692</start>
<end>713</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Large Language Models can Share Images, Too!
%A Lee, Young-Jun
%A Lee, Dokyong
%A Sung, Joo Won
%A Hyeon, Jonghwan
%A Choi, Ho-Jin
%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 lee-etal-2024-large
%X This paper explores the image-sharing capability of Large Language Models (LLMs), such as GPT-4 and LLaMA 2, in a zero-shot setting. To facilitate a comprehensive evaluation of LLMs, we introduce the photochatplus dataset, which includes enriched annotations (ie intent, triggering sentence, image description, and salient information). Furthermore, we present the gradient-free and extensible Decide, Describe, and Retrieve () framework. With extensive experiments, we unlock the image-sharing capability of equipped with LLMs in zero-shot prompting, with ChatGPT achieving the best performance.Our findings also reveal the emergent image-sharing ability in LLMs under zero-shot conditions, validating the effectiveness of . We use this framework to demonstrate its practicality and effectiveness in two real-world scenarios: (1) human-bot interaction and (2) dataset augmentation. To the best of our knowledge, this is the first study to assess the image-sharing ability of various LLMs in a zero-shot setting. We make our source code and dataset publicly available at https://github.com/passing2961/DribeR.
%R 10.18653/v1/2024.findings-acl.39
%U https://aclanthology.org/2024.findings-acl.39/
%U https://doi.org/10.18653/v1/2024.findings-acl.39
%P 692-713
Markdown (Informal)
[Large Language Models can Share Images, Too!](https://aclanthology.org/2024.findings-acl.39/) (Lee et al., Findings 2024)
ACL
- Young-Jun Lee, Dokyong Lee, Joo Won Sung, Jonghwan Hyeon, and Ho-Jin Choi. 2024. Large Language Models can Share Images, Too!. In Findings of the Association for Computational Linguistics: ACL 2024, pages 692–713, Bangkok, Thailand. Association for Computational Linguistics.