mlsanityData to 14 Oct 2026

LogicQA: Logical Anomaly Detection with Vision Language Model Generated Questions

arXiv 2503.20252 ↗First posted 26 Mar 2025cs.CV cs.AIcited by 9

Not on the map. Why?

Abstract (arXiv)

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 percent and an F1-max of 87.0 percent 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.

Key facts. Cited by 9 papers in the map (data through 14 Oct 2026). Builds on 28 of its 44 references that are in the map. First posted on arXiv 26 Mar 2025.

Builds on

28 of 44 references.

References · 28

  1. 2023Improved Baselines with Visual Instruction Tuningcited by 4,418
  2. 2022Large Language Models are Zero-Shot Reasonerscited by 4,374
  3. 2023Lost in the Middle: How Language Models Use Long Contextscited by 3,455
  4. 2023Grounding DINO: Marrying DINO with Grounded Pre-Training for Open-Set Object Detectioncited by 3,332
  5. 2022Language Models (Mostly) Know What They Knowcited by 1,856
  6. 2022Large Language Models Are Human-Level Prompt Engineerscited by 1,045
  7. 2021Towards Total Recall in Industrial Anomaly Detectioncited by 776
  8. 2023EfficientAD: Accurate Visual Anomaly Detection at Millisecond-Level Latenciescited by 160
  9. 2023Deep Industrial Image Anomaly Detection: A Surveycited by 148
  10. 2022Asymmetric Student-Teacher Networks for Industrial Anomaly Detectioncited by 117
  11. 2024Interpreting and Editing Vision-Language Representations to Mitigate Hallucinationscited by 104
  12. 2024Why are Visually-Grounded Language Models Bad at Image Classification?cited by 102
16 more
  1. 2024Understanding the Limits of Vision Language Models Through the Lens of the Binding Problemcited by 75
  2. 2021Towards Few-Shot Fact-Checking via Perplexitycited by 63
  3. 2022A Survey on Explainable Anomaly Detectioncited by 39
  4. 2025LogicAD: Explainable Anomaly Detection via VLM-based Text Feature Extractioncited by 25
  5. 2023Component-aware anomaly detection framework for adjustable and logical industrial visual inspectioncited by 22
  6. 2023Few Shot Part Segmentation Reveals Compositional Logic for Industrial Anomaly Detectioncited by 19
  7. 2024LogiCode: an LLM-Driven Framework for Logical Anomaly Detectioncited by 19
  8. 2024CSAD: Unsupervised Component Segmentation for Logical Anomaly Detectioncited by 12
  9. 2025GCAD: Anomaly Detection in Multivariate Time Series from the Perspective of Granger Causalitycited by 12
  10. 2023UniFormaly: Towards Task-Agnostic Unified Framework for Visual Anomaly Detectioncited by 11
  11. 2024Guiding Vision-Language Model Selection for Visual Question-Answering Across Tasks, Domains, and Knowledge Typescited by 10
  12. 2024Hierarchical Deconstruction of LLM Reasoning: A Graph-Based Framework for Analyzing Knowledge Utilizationcited by 9
  13. 2022A general-purpose method for applying Explainable AI for Anomaly Detectioncited by 7
  14. 2024ProbGate at EHRSQL 2024: Enhancing SQL Query Generation Accuracy through Probabilistic Threshold Filtering and Error Handlingcited by 7
  15. 2024Decompose and Compare Consistency: Measuring VLMs' Answer Reliability via Task-Decomposition Consistency Comparisoncited by 7
  16. 2024Interactive Explainable Anomaly Detection for Industrial Settingscited by 1

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2025: 3; 2026: 6.

9 papers.

  1. 2025IAD-R1: Reinforcing Consistent Reasoning in Industrial Anomaly Detectioncited by 17
  2. 2025Hold Onto That Thought: Assessing KV Cache Compression On Reasoningcited by 6
  3. 2026FORGE: Fine-grained Multimodal Evaluation for Manufacturing Scenarioscited by 2
  4. 2026Probe-VAD: Ordinal Likelihood Probing for Training-Free Video Anomaly Detectioncited by 1
  5. 2025TMUAD: Enhancing Logical Capabilities in Unified Anomaly Detection Models with a Text Memory Bankcited by 0
  6. 2026DifferAD-R1: A Difference-Guided IndustrialAnomaly Localization with Multimodal LargeLanguage Modelscited by 0
  7. 2026LADBench: A Benchmark for Logical Fault Detection in Imagescited by 0
  8. 2026Deep Interaction: An Efficient Human-AI Interaction Method for Large Reasoning Modelscited by 0
  9. 2026Are you Talking Logic to Me? Assessing Language Models Syllogistic Reasoning Capabilitiescited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2026Interpretable Logical Anomaly Classification via Constraint Decomposition and Instruction Fine-Tuning
  2. 2024Separating Novel Features for Logical Anomaly Detection: A Straightforward yet Effective Approach
  3. 2025SAGE: A Visual Language Model for Anomaly Detection via Fact Enhancement and Entropy-aware Alignment
  4. 2025Detect, Classify, Act: Categorizing Industrial Anomalies with Multi-Modal Large Language Models
  5. 2025LAD-Reasoner: Tiny Multimodal Models are Good Reasoners for Logical Anomaly Detection
  6. 2025EIAD: Explainable Industrial Anomaly Detection Via Multi-Modal Large Language Models
  7. 2025Towards Training-free Anomaly Detection with Vision and Language Foundation Models
  8. 2026InspectorGPT: A Comparative Reasoning Enhanced VLM for Comprehensive Industrial Anomaly Detection