@inproceedings{agarwal-etal-2024-indifoodvqa,
title = "{I}ndi{F}ood{VQA}: Advancing Visual Question Answering and Reasoning with a Knowledge-Infused Synthetic Data Generation Pipeline",
author = "Agarwal, Pulkit and
Sravanthi, Settaluri and
Bhattacharyya, Pushpak",
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.78/",
pages = "1158--1176",
abstract = "Large Vision Language Models (VLMs) like GPT-4, LLaVA, and InstructBLIP exhibit extraordinary capabilities for both knowledge understanding and reasoning. However, the reasoning capabilities of such models on sophisticated problems that require external knowledge of a specific domain have not been assessed well, due to the unavailability of necessary datasets. In this work, we release a first-of-its-kind dataset called IndiFoodVQA with around 16.7k data samples, consisting of explicit knowledge-infused questions, answers, and reasons. We also release IndiFoodKG, a related Knowledge Graph (KG) with 79k triples. The data has been created with minimal human intervention via an automated pipeline based on InstructBlip and GPT-3.5. We also present a methodology to extract knowledge from the KG and use it to both answer and reason upon the questions. We employ different models to report baseline zero-shot and fine-tuned results. Fine-tuned VLMs on our data showed an improvement of {\textasciitilde}25{\%} over the corresponding base model, highlighting the fact that current VLMs need domain-specific fine-tuning to excel in specialized settings. Our findings reveal that (1) explicit knowledge infusion during question generation helps in making questions that have more grounded knowledge, and (2) proper knowledge retrieval can often lead to better-answering potential in such cases. The data and code is available at https://github.com/SLSravanthi/IndifoodVQA."
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="agarwal-etal-2024-indifoodvqa">
<titleInfo>
<title>IndiFoodVQA: Advancing Visual Question Answering and Reasoning with a Knowledge-Infused Synthetic Data Generation Pipeline</title>
</titleInfo>
<name type="personal">
<namePart type="given">Pulkit</namePart>
<namePart type="family">Agarwal</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Settaluri</namePart>
<namePart type="family">Sravanthi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Pushpak</namePart>
<namePart type="family">Bhattacharyya</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>Large Vision Language Models (VLMs) like GPT-4, LLaVA, and InstructBLIP exhibit extraordinary capabilities for both knowledge understanding and reasoning. However, the reasoning capabilities of such models on sophisticated problems that require external knowledge of a specific domain have not been assessed well, due to the unavailability of necessary datasets. In this work, we release a first-of-its-kind dataset called IndiFoodVQA with around 16.7k data samples, consisting of explicit knowledge-infused questions, answers, and reasons. We also release IndiFoodKG, a related Knowledge Graph (KG) with 79k triples. The data has been created with minimal human intervention via an automated pipeline based on InstructBlip and GPT-3.5. We also present a methodology to extract knowledge from the KG and use it to both answer and reason upon the questions. We employ different models to report baseline zero-shot and fine-tuned results. Fine-tuned VLMs on our data showed an improvement of ~25% over the corresponding base model, highlighting the fact that current VLMs need domain-specific fine-tuning to excel in specialized settings. Our findings reveal that (1) explicit knowledge infusion during question generation helps in making questions that have more grounded knowledge, and (2) proper knowledge retrieval can often lead to better-answering potential in such cases. The data and code is available at https://github.com/SLSravanthi/IndifoodVQA.</abstract>
<identifier type="citekey">agarwal-etal-2024-indifoodvqa</identifier>
<location>
<url>https://aclanthology.org/2024.findings-eacl.78/</url>
</location>
<part>
<date>2024-03</date>
<extent unit="page">
<start>1158</start>
<end>1176</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T IndiFoodVQA: Advancing Visual Question Answering and Reasoning with a Knowledge-Infused Synthetic Data Generation Pipeline
%A Agarwal, Pulkit
%A Sravanthi, Settaluri
%A Bhattacharyya, Pushpak
%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 agarwal-etal-2024-indifoodvqa
%X Large Vision Language Models (VLMs) like GPT-4, LLaVA, and InstructBLIP exhibit extraordinary capabilities for both knowledge understanding and reasoning. However, the reasoning capabilities of such models on sophisticated problems that require external knowledge of a specific domain have not been assessed well, due to the unavailability of necessary datasets. In this work, we release a first-of-its-kind dataset called IndiFoodVQA with around 16.7k data samples, consisting of explicit knowledge-infused questions, answers, and reasons. We also release IndiFoodKG, a related Knowledge Graph (KG) with 79k triples. The data has been created with minimal human intervention via an automated pipeline based on InstructBlip and GPT-3.5. We also present a methodology to extract knowledge from the KG and use it to both answer and reason upon the questions. We employ different models to report baseline zero-shot and fine-tuned results. Fine-tuned VLMs on our data showed an improvement of ~25% over the corresponding base model, highlighting the fact that current VLMs need domain-specific fine-tuning to excel in specialized settings. Our findings reveal that (1) explicit knowledge infusion during question generation helps in making questions that have more grounded knowledge, and (2) proper knowledge retrieval can often lead to better-answering potential in such cases. The data and code is available at https://github.com/SLSravanthi/IndifoodVQA.
%U https://aclanthology.org/2024.findings-eacl.78/
%P 1158-1176
Markdown (Informal)
[IndiFoodVQA: Advancing Visual Question Answering and Reasoning with a Knowledge-Infused Synthetic Data Generation Pipeline](https://aclanthology.org/2024.findings-eacl.78/) (Agarwal et al., Findings 2024)
ACL