@inproceedings{cao-jiang-2024-knowledge,
title = "Knowledge Generation for Zero-shot Knowledge-based {VQA}",
author = "Cao, Rui and
Jiang, Jing",
editor = "Graham, Yvette and
Purver, Matthew",
booktitle = "Findings of the Association for Computational Linguistics: EACL 2024",
month = mar,
year = "2024",
address = "St. Julian{'}s, Malta",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2024.findings-eacl.36",
pages = "533--549",
abstract = "Previous solutions to knowledge-based visual question answering (K-VQA) retrieve knowledge from external knowledge bases and use supervised learning to train the K-VQA model.Recently pre-trained LLMs have been used as both a knowledge source and a zero-shot QA model for K-VQA and demonstrated promising results.However, these recent methods do not explicitly show the knowledge needed to answer the questions and thus lack interpretability.Inspired by recent work on knowledge generation from LLMs for text-based QA, in this work we propose and test a similar knowledge-generation-based K-VQA method, which first generates knowledge from an LLM and then incorporates the generated knowledge for K-VQA in a zero-shot manner. We evaluate our method on two K-VQA benchmarks and found that our method performs better than previous zero-shot K-VQA methods and our generated knowledge is generally relevant and helpful.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="cao-jiang-2024-knowledge">
<titleInfo>
<title>Knowledge Generation for Zero-shot Knowledge-based VQA</title>
</titleInfo>
<name type="personal">
<namePart type="given">Rui</namePart>
<namePart type="family">Cao</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jing</namePart>
<namePart type="family">Jiang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2024-03</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Findings of the Association for Computational Linguistics: EACL 2024</title>
</titleInfo>
<name type="personal">
<namePart type="given">Yvette</namePart>
<namePart type="family">Graham</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Matthew</namePart>
<namePart type="family">Purver</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">St. Julian’s, Malta</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Previous solutions to knowledge-based visual question answering (K-VQA) retrieve knowledge from external knowledge bases and use supervised learning to train the K-VQA model.Recently pre-trained LLMs have been used as both a knowledge source and a zero-shot QA model for K-VQA and demonstrated promising results.However, these recent methods do not explicitly show the knowledge needed to answer the questions and thus lack interpretability.Inspired by recent work on knowledge generation from LLMs for text-based QA, in this work we propose and test a similar knowledge-generation-based K-VQA method, which first generates knowledge from an LLM and then incorporates the generated knowledge for K-VQA in a zero-shot manner. We evaluate our method on two K-VQA benchmarks and found that our method performs better than previous zero-shot K-VQA methods and our generated knowledge is generally relevant and helpful.</abstract>
<identifier type="citekey">cao-jiang-2024-knowledge</identifier>
<location>
<url>https://aclanthology.org/2024.findings-eacl.36</url>
</location>
<part>
<date>2024-03</date>
<extent unit="page">
<start>533</start>
<end>549</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Knowledge Generation for Zero-shot Knowledge-based VQA
%A Cao, Rui
%A Jiang, Jing
%Y Graham, Yvette
%Y Purver, Matthew
%S Findings of the Association for Computational Linguistics: EACL 2024
%D 2024
%8 March
%I Association for Computational Linguistics
%C St. Julian’s, Malta
%F cao-jiang-2024-knowledge
%X Previous solutions to knowledge-based visual question answering (K-VQA) retrieve knowledge from external knowledge bases and use supervised learning to train the K-VQA model.Recently pre-trained LLMs have been used as both a knowledge source and a zero-shot QA model for K-VQA and demonstrated promising results.However, these recent methods do not explicitly show the knowledge needed to answer the questions and thus lack interpretability.Inspired by recent work on knowledge generation from LLMs for text-based QA, in this work we propose and test a similar knowledge-generation-based K-VQA method, which first generates knowledge from an LLM and then incorporates the generated knowledge for K-VQA in a zero-shot manner. We evaluate our method on two K-VQA benchmarks and found that our method performs better than previous zero-shot K-VQA methods and our generated knowledge is generally relevant and helpful.
%U https://aclanthology.org/2024.findings-eacl.36
%P 533-549
Markdown (Informal)
[Knowledge Generation for Zero-shot Knowledge-based VQA](https://aclanthology.org/2024.findings-eacl.36) (Cao & Jiang, Findings 2024)
ACL