@inproceedings{hasegawa-etal-2025-promqa,
title = "{P}ro{MQA}: Question Answering Dataset for Multimodal Procedural Activity Understanding",
author = "Hasegawa, Kimihiro and
Imrattanatrai, Wiradee and
Cheng, Zhi-Qi and
Asada, Masaki and
Holm, Susan and
Wang, Yuran and
Fukuda, Ken and
Mitamura, Teruko",
editor = "Chiruzzo, Luis and
Ritter, Alan and
Wang, Lu",
booktitle = "Proceedings of the 2025 Conference of the Nations of the Americas Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 1: Long Papers)",
month = apr,
year = "2025",
address = "Albuquerque, New Mexico",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2025.naacl-long.579/",
doi = "10.18653/v1/2025.naacl-long.579",
pages = "11598--11617",
ISBN = "979-8-89176-189-6",
abstract = "Multimodal systems have great potential to assist humans in procedural activities, where people follow instructions to achieve their goals. Despite diverse application scenarios, systems are typically evaluated on traditional classification tasks, e.g., action recognition or temporal action localization. In this paper, we present a novel evaluation dataset, ProMQA, to measure the advancement of systems in application-oriented scenarios. ProMQA consists of 401 multimodal procedural QA pairs on user recording of procedural activities, i.e., cooking, coupled with their corresponding instruction. For QA annotation, we take a cost-effective human-LLM collaborative approach, where the existing annotation is augmented with LLM-generated QA pairs that are later verified by humans. We then provide the benchmark results to set the baseline performance on ProMQA. Our experiment reveals a significant gap between human performance and that of current systems, including competitive proprietary multimodal models. We hope our dataset sheds light on new aspects of models' multimodal understanding capabilities."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="hasegawa-etal-2025-promqa">
<titleInfo>
<title>ProMQA: Question Answering Dataset for Multimodal Procedural Activity Understanding</title>
</titleInfo>
<name type="personal">
<namePart type="given">Kimihiro</namePart>
<namePart type="family">Hasegawa</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Wiradee</namePart>
<namePart type="family">Imrattanatrai</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Zhi-Qi</namePart>
<namePart type="family">Cheng</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Masaki</namePart>
<namePart type="family">Asada</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Susan</namePart>
<namePart type="family">Holm</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yuran</namePart>
<namePart type="family">Wang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ken</namePart>
<namePart type="family">Fukuda</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Teruko</namePart>
<namePart type="family">Mitamura</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2025-04</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 2025 Conference of the Nations of the Americas Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 1: Long Papers)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Luis</namePart>
<namePart type="family">Chiruzzo</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Alan</namePart>
<namePart type="family">Ritter</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Lu</namePart>
<namePart type="family">Wang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Albuquerque, New Mexico</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-8-89176-189-6</identifier>
</relatedItem>
<abstract>Multimodal systems have great potential to assist humans in procedural activities, where people follow instructions to achieve their goals. Despite diverse application scenarios, systems are typically evaluated on traditional classification tasks, e.g., action recognition or temporal action localization. In this paper, we present a novel evaluation dataset, ProMQA, to measure the advancement of systems in application-oriented scenarios. ProMQA consists of 401 multimodal procedural QA pairs on user recording of procedural activities, i.e., cooking, coupled with their corresponding instruction. For QA annotation, we take a cost-effective human-LLM collaborative approach, where the existing annotation is augmented with LLM-generated QA pairs that are later verified by humans. We then provide the benchmark results to set the baseline performance on ProMQA. Our experiment reveals a significant gap between human performance and that of current systems, including competitive proprietary multimodal models. We hope our dataset sheds light on new aspects of models’ multimodal understanding capabilities.</abstract>
<identifier type="citekey">hasegawa-etal-2025-promqa</identifier>
<identifier type="doi">10.18653/v1/2025.naacl-long.579</identifier>
<location>
<url>https://aclanthology.org/2025.naacl-long.579/</url>
</location>
<part>
<date>2025-04</date>
<extent unit="page">
<start>11598</start>
<end>11617</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T ProMQA: Question Answering Dataset for Multimodal Procedural Activity Understanding
%A Hasegawa, Kimihiro
%A Imrattanatrai, Wiradee
%A Cheng, Zhi-Qi
%A Asada, Masaki
%A Holm, Susan
%A Wang, Yuran
%A Fukuda, Ken
%A Mitamura, Teruko
%Y Chiruzzo, Luis
%Y Ritter, Alan
%Y Wang, Lu
%S Proceedings of the 2025 Conference of the Nations of the Americas Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 1: Long Papers)
%D 2025
%8 April
%I Association for Computational Linguistics
%C Albuquerque, New Mexico
%@ 979-8-89176-189-6
%F hasegawa-etal-2025-promqa
%X Multimodal systems have great potential to assist humans in procedural activities, where people follow instructions to achieve their goals. Despite diverse application scenarios, systems are typically evaluated on traditional classification tasks, e.g., action recognition or temporal action localization. In this paper, we present a novel evaluation dataset, ProMQA, to measure the advancement of systems in application-oriented scenarios. ProMQA consists of 401 multimodal procedural QA pairs on user recording of procedural activities, i.e., cooking, coupled with their corresponding instruction. For QA annotation, we take a cost-effective human-LLM collaborative approach, where the existing annotation is augmented with LLM-generated QA pairs that are later verified by humans. We then provide the benchmark results to set the baseline performance on ProMQA. Our experiment reveals a significant gap between human performance and that of current systems, including competitive proprietary multimodal models. We hope our dataset sheds light on new aspects of models’ multimodal understanding capabilities.
%R 10.18653/v1/2025.naacl-long.579
%U https://aclanthology.org/2025.naacl-long.579/
%U https://doi.org/10.18653/v1/2025.naacl-long.579
%P 11598-11617
Markdown (Informal)
[ProMQA: Question Answering Dataset for Multimodal Procedural Activity Understanding](https://aclanthology.org/2025.naacl-long.579/) (Hasegawa et al., NAACL 2025)
ACL
- Kimihiro Hasegawa, Wiradee Imrattanatrai, Zhi-Qi Cheng, Masaki Asada, Susan Holm, Yuran Wang, Ken Fukuda, and Teruko Mitamura. 2025. ProMQA: Question Answering Dataset for Multimodal Procedural Activity Understanding. In Proceedings of the 2025 Conference of the Nations of the Americas Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 1: Long Papers), pages 11598–11617, Albuquerque, New Mexico. Association for Computational Linguistics.