@inproceedings{kwon-etal-2025-logicqa,
title = "{L}ogic{QA}: Logical Anomaly Detection with Vision Language Model Generated Questions",
author = "Kwon, Yejin and
Moon, Daeun and
Oh, Youngje and
Yoon, Hyunsoo",
editor = "Rehm, Georg and
Li, Yunyao",
booktitle = "Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 6: Industry Track)",
month = jul,
year = "2025",
address = "Vienna, Austria",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2025.acl-industry.29/",
doi = "10.18653/v1/2025.acl-industry.29",
pages = "411--432",
ISBN = "979-8-89176-288-6",
abstract = "Anomaly Detection (AD) focuses on detecting samples that differ from the standard pattern, making it a vital tool in process control. Logical anomalies may appear visually normal yet violate predefined constraints on object presence, arrangement, or quantity, depending on reasoning and explainability. We introduce LogicQA, a framework that enhances AD by providing industrial operators with explanations for logical anomalies. LogicQA compiles automatically generated questions into a checklist and collects responses to identify violations of logical constraints. LogicQA is training-free, annotation-free, and operates in a few-shot setting. We achieve state-of-the-art (SOTA) Logical AD performance on public benchmarks, MVTec LOCO AD, with an AUROC of 87.6{\%} and an $F_1$-max of 87.0{\%} along with the explanations of anomalies. Also, our approach has shown outstanding performance on semiconductor SEM corporate data, further validating its effectiveness in industrial applications."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="kwon-etal-2025-logicqa">
<titleInfo>
<title>LogicQA: Logical Anomaly Detection with Vision Language Model Generated Questions</title>
</titleInfo>
<name type="personal">
<namePart type="given">Yejin</namePart>
<namePart type="family">Kwon</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Daeun</namePart>
<namePart type="family">Moon</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Youngje</namePart>
<namePart type="family">Oh</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hyunsoo</namePart>
<namePart type="family">Yoon</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2025-07</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 6: Industry Track)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Georg</namePart>
<namePart type="family">Rehm</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yunyao</namePart>
<namePart type="family">Li</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Vienna, Austria</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-8-89176-288-6</identifier>
</relatedItem>
<abstract>Anomaly Detection (AD) focuses on detecting samples that differ from the standard pattern, making it a vital tool in process control. Logical anomalies may appear visually normal yet violate predefined constraints on object presence, arrangement, or quantity, depending on reasoning and explainability. We introduce LogicQA, a framework that enhances AD by providing industrial operators with explanations for logical anomalies. LogicQA compiles automatically generated questions into a checklist and collects responses to identify violations of logical constraints. LogicQA is training-free, annotation-free, and operates in a few-shot setting. We achieve state-of-the-art (SOTA) Logical AD performance on public benchmarks, MVTec LOCO AD, with an AUROC of 87.6% and an F₁-max of 87.0% along with the explanations of anomalies. Also, our approach has shown outstanding performance on semiconductor SEM corporate data, further validating its effectiveness in industrial applications.</abstract>
<identifier type="citekey">kwon-etal-2025-logicqa</identifier>
<identifier type="doi">10.18653/v1/2025.acl-industry.29</identifier>
<location>
<url>https://aclanthology.org/2025.acl-industry.29/</url>
</location>
<part>
<date>2025-07</date>
<extent unit="page">
<start>411</start>
<end>432</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T LogicQA: Logical Anomaly Detection with Vision Language Model Generated Questions
%A Kwon, Yejin
%A Moon, Daeun
%A Oh, Youngje
%A Yoon, Hyunsoo
%Y Rehm, Georg
%Y Li, Yunyao
%S Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 6: Industry Track)
%D 2025
%8 July
%I Association for Computational Linguistics
%C Vienna, Austria
%@ 979-8-89176-288-6
%F kwon-etal-2025-logicqa
%X Anomaly Detection (AD) focuses on detecting samples that differ from the standard pattern, making it a vital tool in process control. Logical anomalies may appear visually normal yet violate predefined constraints on object presence, arrangement, or quantity, depending on reasoning and explainability. We introduce LogicQA, a framework that enhances AD by providing industrial operators with explanations for logical anomalies. LogicQA compiles automatically generated questions into a checklist and collects responses to identify violations of logical constraints. LogicQA is training-free, annotation-free, and operates in a few-shot setting. We achieve state-of-the-art (SOTA) Logical AD performance on public benchmarks, MVTec LOCO AD, with an AUROC of 87.6% and an F₁-max of 87.0% along with the explanations of anomalies. Also, our approach has shown outstanding performance on semiconductor SEM corporate data, further validating its effectiveness in industrial applications.
%R 10.18653/v1/2025.acl-industry.29
%U https://aclanthology.org/2025.acl-industry.29/
%U https://doi.org/10.18653/v1/2025.acl-industry.29
%P 411-432
Markdown (Informal)
[LogicQA: Logical Anomaly Detection with Vision Language Model Generated Questions](https://aclanthology.org/2025.acl-industry.29/) (Kwon et al., ACL 2025)
ACL