LogicQA: Logical Anomaly Detection with Vision Language Model Generated Questions

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 the public benchmark, 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. 1 2 3 1 2 3 Main Questions 1. Are there exactly two splicing connectors in the image? 2. Are the connectors rectangular and compact, each containing five clamps? 8. Does the cable connect the two connectors in a way that creates mirror symmetry? ... Filtered questions ( Normal set accuracy < 0.8 ) Query Image Main Questions Q1. Are there exactly two splicing connectors in the image? Q2. Are the connectors rectangular and compact, each containing five clamps? …