@inproceedings{zhao-etal-2023-retrieving,
title = "Retrieving Multimodal Information for Augmented Generation: A Survey",
author = "Zhao, Ruochen and
Chen, Hailin and
Wang, Weishi and
Jiao, Fangkai and
Do, Xuan Long and
Qin, Chengwei and
Ding, Bosheng and
Guo, Xiaobao and
Li, Minzhi and
Li, Xingxuan and
Joty, Shafiq",
editor = "Bouamor, Houda and
Pino, Juan and
Bali, Kalika",
booktitle = "Findings of the Association for Computational Linguistics: EMNLP 2023",
month = dec,
year = "2023",
address = "Singapore",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2023.findings-emnlp.314/",
doi = "10.18653/v1/2023.findings-emnlp.314",
pages = "4736--4756",
abstract = "As Large Language Models (LLMs) become popular, there emerged an important trend of using multimodality to augment the LLMs' generation ability, which enables LLMs to better interact with the world. However, there lacks a unified perception of at which stage and how to incorporate different modalities. In this survey, we review methods that assist and augment generative models by retrieving multimodal knowledge, whose formats range from images, codes, tables, graphs, to audio. Such methods offer a promising solution to important concerns such as factuality, reasoning, interpretability, and robustness. By providing an in-depth review, this survey is expected to provide scholars with a deeper understanding of the methods' applications and encourage them to adapt existing techniques to the fast-growing field of LLMs."
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="zhao-etal-2023-retrieving">
<titleInfo>
<title>Retrieving Multimodal Information for Augmented Generation: A Survey</title>
</titleInfo>
<name type="personal">
<namePart type="given">Ruochen</namePart>
<namePart type="family">Zhao</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hailin</namePart>
<namePart type="family">Chen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Weishi</namePart>
<namePart type="family">Wang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Fangkai</namePart>
<namePart type="family">Jiao</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Xuan</namePart>
<namePart type="given">Long</namePart>
<namePart type="family">Do</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Chengwei</namePart>
<namePart type="family">Qin</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Bosheng</namePart>
<namePart type="family">Ding</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Xiaobao</namePart>
<namePart type="family">Guo</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Minzhi</namePart>
<namePart type="family">Li</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Xingxuan</namePart>
<namePart type="family">Li</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Shafiq</namePart>
<namePart type="family">Joty</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2023-12</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Findings of the Association for Computational Linguistics: EMNLP 2023</title>
</titleInfo>
<name type="personal">
<namePart type="given">Houda</namePart>
<namePart type="family">Bouamor</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Juan</namePart>
<namePart type="family">Pino</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Kalika</namePart>
<namePart type="family">Bali</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Singapore</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>As Large Language Models (LLMs) become popular, there emerged an important trend of using multimodality to augment the LLMs’ generation ability, which enables LLMs to better interact with the world. However, there lacks a unified perception of at which stage and how to incorporate different modalities. In this survey, we review methods that assist and augment generative models by retrieving multimodal knowledge, whose formats range from images, codes, tables, graphs, to audio. Such methods offer a promising solution to important concerns such as factuality, reasoning, interpretability, and robustness. By providing an in-depth review, this survey is expected to provide scholars with a deeper understanding of the methods’ applications and encourage them to adapt existing techniques to the fast-growing field of LLMs.</abstract>
<identifier type="citekey">zhao-etal-2023-retrieving</identifier>
<identifier type="doi">10.18653/v1/2023.findings-emnlp.314</identifier>
<location>
<url>https://aclanthology.org/2023.findings-emnlp.314/</url>
</location>
<part>
<date>2023-12</date>
<extent unit="page">
<start>4736</start>
<end>4756</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Retrieving Multimodal Information for Augmented Generation: A Survey
%A Zhao, Ruochen
%A Chen, Hailin
%A Wang, Weishi
%A Jiao, Fangkai
%A Do, Xuan Long
%A Qin, Chengwei
%A Ding, Bosheng
%A Guo, Xiaobao
%A Li, Minzhi
%A Li, Xingxuan
%A Joty, Shafiq
%Y Bouamor, Houda
%Y Pino, Juan
%Y Bali, Kalika
%S Findings of the Association for Computational Linguistics: EMNLP 2023
%D 2023
%8 December
%I Association for Computational Linguistics
%C Singapore
%F zhao-etal-2023-retrieving
%X As Large Language Models (LLMs) become popular, there emerged an important trend of using multimodality to augment the LLMs’ generation ability, which enables LLMs to better interact with the world. However, there lacks a unified perception of at which stage and how to incorporate different modalities. In this survey, we review methods that assist and augment generative models by retrieving multimodal knowledge, whose formats range from images, codes, tables, graphs, to audio. Such methods offer a promising solution to important concerns such as factuality, reasoning, interpretability, and robustness. By providing an in-depth review, this survey is expected to provide scholars with a deeper understanding of the methods’ applications and encourage them to adapt existing techniques to the fast-growing field of LLMs.
%R 10.18653/v1/2023.findings-emnlp.314
%U https://aclanthology.org/2023.findings-emnlp.314/
%U https://doi.org/10.18653/v1/2023.findings-emnlp.314
%P 4736-4756
Markdown (Informal)
[Retrieving Multimodal Information for Augmented Generation: A Survey](https://aclanthology.org/2023.findings-emnlp.314/) (Zhao et al., Findings 2023)
ACL
- Ruochen Zhao, Hailin Chen, Weishi Wang, Fangkai Jiao, Xuan Long Do, Chengwei Qin, Bosheng Ding, Xiaobao Guo, Minzhi Li, Xingxuan Li, and Shafiq Joty. 2023. Retrieving Multimodal Information for Augmented Generation: A Survey. In Findings of the Association for Computational Linguistics: EMNLP 2023, pages 4736–4756, Singapore. Association for Computational Linguistics.