Large Language Models can Share Images, Too!

Fuente: arXiv
Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Lee, Young-Jun, Lee, Dokyong, Sung, Joo Won, Hyeon, Jonghwan, Choi, Ho-Jin
Format: Preprint
Veröffentlicht: 2023
Schlagworte:
Online-Zugang:
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866910513541152768
author Lee, Young-Jun
Lee, Dokyong
Sung, Joo Won
Hyeon, Jonghwan
Choi, Ho-Jin
author_facet Lee, Young-Jun
Lee, Dokyong
Sung, Joo Won
Hyeon, Jonghwan
Choi, Ho-Jin
contents 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 PhotoChat++ dataset, which includes enriched annotations (i.e., intent, triggering sentence, image description, and salient information). Furthermore, we present the gradient-free and extensible Decide, Describe, and Retrieve (DribeR) framework. With extensive experiments, we unlock the image-sharing capability of DribeR 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 DribeR. 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.
format Preprint
id arxiv_https___arxiv_org_abs_2310_14804
institution arXiv
publishDate 2023
record_format arxiv
spellingShingle Large Language Models can Share Images, Too!
Lee, Young-Jun
Lee, Dokyong
Sung, Joo Won
Hyeon, Jonghwan
Choi, Ho-Jin
Computer Vision and Pattern Recognition
Artificial Intelligence
Computation and Language
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 PhotoChat++ dataset, which includes enriched annotations (i.e., intent, triggering sentence, image description, and salient information). Furthermore, we present the gradient-free and extensible Decide, Describe, and Retrieve (DribeR) framework. With extensive experiments, we unlock the image-sharing capability of DribeR 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 DribeR. 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.
title Large Language Models can Share Images, Too!
topic Computer Vision and Pattern Recognition
Artificial Intelligence
Computation and Language
url https://arxiv.org/abs/2310.14804