mlsanityData to 7 Oct 2026

CAVE: Detecting and Explaining Commonsense Anomalies in Visual Environments

arXiv 2510.26006 ↗First posted 29 Oct 2025cs.CV cs.CLcited by 3

Not on the map. Why?

Abstract (arXiv)

Humans can naturally identify, reason about, and explain anomalies in their environment. In computer vision, this long-standing challenge remains limited to industrial defects or unrealistic, synthetically generated anomalies, failing to capture the richness and unpredictability of real-world anomalies. In this work, we introduce CAVE, the first benchmark of real-world visual anomalies. CAVE supports three open-ended tasks: anomaly description, explanation, and justification; with fine-grained annotations for visual grounding and categorizing anomalies based on their visual manifestations, their complexity, severity, and commonness. These annotations draw inspiration from cognitive science research on how humans identify and resolve anomalies, providing a comprehensive framework for evaluating Vision-Language Models (VLMs) in detecting and understanding anomalies. We show that state-of-the-art VLMs struggle with visual anomaly perception and commonsense reasoning, even with advanced prompting strategies. By offering a realistic and cognitively grounded benchmark, CAVE serves as a valuable resource for advancing research in anomaly detection and commonsense reasoning in VLMs.

Key facts. Cited by 3 papers in the map (data through 7 Oct 2026). Builds on 32 of its 68 references that are in the map. First posted on arXiv 29 Oct 2025.

Builds on

32 of 68 references.

References · 32

  1. 2022Chain-of-Thought Prompting Elicits Reasoning in Large Language Modelscited by 12,302
  2. 2023Judging LLM-as-a-Judge with MT-Bench and Chatbot Arenacited by 8,393
  3. 2022Self-Consistency Improves Chain of Thought Reasoning in Language Modelscited by 5,601
  4. 2023Grounding DINO: Marrying DINO with Grounded Pre-Training for Open-Set Object Detectioncited by 3,274
  5. 2024LLaVA-OneVision: Easy Visual Task Transfercited by 2,669
  6. 2023The Dawn of LMMs: Preliminary Explorations with GPT-4V(ision)cited by 677
  7. 2018Real-world Anomaly Detection in Surveillance Videoscited by 570
  8. 2018From Recognition to Cognition: Visual Commonsense Reasoningcited by 553
  9. 2022Winoground: Probing Vision and Language Models for Visio-Linguistic Compositionalitycited by 523
  10. 2024LLaVA-CoT: Let Vision Language Models Reason Step-by-Stepcited by 446
  11. 2024Prismatic VLMs: Investigating the Design Space of Visually-Conditioned Language Modelscited by 336
  12. 2021VT-ADL: A Vision Transformer Network for Image Anomaly Detection and Localizationcited by 222
20 more
  1. 2024Aligning with Human Judgement: The Role of Pairwise Preference in Large Language Model Evaluatorscited by 146
  2. 2020Deep Learning for Medical Anomaly Detection -- A Surveycited by 127
  3. 2022Anomaly Detection in Autonomous Driving: A Surveycited by 87
  4. 2023Breaking Common Sense: WHOOPS! A Vision-and-Language Benchmark of Synthetic and Compositional Imagescited by 79
  5. 2024Understanding the Limits of Vision Language Models Through the Lens of the Binding Problemcited by 71
  6. 2024A Survey on Visual Anomaly Detection: Challenge, Approach, and Prospectcited by 69
  7. 2017Automatic Understanding of Image and Video Advertisementscited by 67
  8. 2023IM-IAD: Industrial Image Anomaly Detection Benchmark in Manufacturingcited by 64
  9. 2024LLMs Meet VLMs: Boost Open Vocabulary Object Detection with Fine-grained Descriptorscited by 39
  10. 2024HaloQuest: A Visual Hallucination Dataset for Advancing Multimodal Reasoningcited by 30
  11. 2020Viral Pneumonia Screening on Chest X-ray Images Using Confidence-Aware Anomaly Detectioncited by 28
  12. 2023ROME: Evaluating Pre-trained Vision-Language Models on Reasoning beyond Visual Common Sensecited by 27
  13. 2023Link-Context Learning for Multimodal LLMscited by 24
  14. 2025Multimodal Inconsistency Reasoning (MMIR): A New Benchmark for Multimodal Reasoning Modelscited by 24
  15. 2023GlitchBench: Can large multimodal models detect video game glitches?cited by 21
  16. 2024PhysGame: Uncovering Physical Commonsense Violations in Gameplay Videoscited by 21
  17. 2025How Well Does GPT-4o Understand Vision? Evaluating Multimodal Foundation Models on Standard Computer Vision Taskscited by 14
  18. 2024"Don't forget to put the milk back!" Dataset for Enabling Embodied Agents to Detect Anomalous Situationscited by 9
  19. 2024Benchmarking VLMs' Reasoning About Persuasive Atypical Imagescited by 5
  20. 2024NEMO: Can Multimodal LLMs Identify Attribute-Modified Objects?cited by 2

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2026: 3.

3 papers.

  1. 2026LADBench: A Benchmark for Logical Fault Detection in Imagescited by 0
  2. 2026Clarify User Expertise: Towards Proactive Conversational Agents Tailoring Responses to User Proficiencycited by 0
  3. 2026AnswerMap: Faithful Spatial Interpretability of VLMs from Answer Posteriorscited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2026Reasoning or Pattern Matching? Probing Large Vision-Language Models with Visual Puzzles
  2. 2025VERIFY: A Benchmark of Visual Explanation and Reasoning for Investigating Multimodal Reasoning Fidelity
  3. 2026TAU-Bench: From Anomaly Instance Tracking to Fine-Grained Video Anomaly Understanding
  4. 2024Black Swan: Abductive and Defeasible Video Reasoning in Unpredictable Events
  5. 2025From Benchmarks to Reality: Advancing Visual Anomaly Detection by the VAND 3.0 Challenge
  6. 2024Bongard in Wonderland: Visual Puzzles that Still Make AI Go Mad?
  7. 2025PRISM-Bench: A Benchmark of Puzzle-Based Visual Tasks with CoT Error Detection
  8. 2026CDH-Bench: A Commonsense-Driven Hallucination Benchmark for Evaluating Visual Fidelity in Vision-Language Models