mlsanityData to 14 Oct 2026

ALARM: Automated MLLM-Based Anomaly Detection in Complex-EnviRonment Monitoring with Uncertainty Quantification

arXiv 2512.03101 ↗First posted 1 Dec 2025cs.LG cs.AI cs.CVcited by 2

On the map: Multimodal LLMs / vision-language models → Chart understanding and anomaly detection

Abstract (arXiv)

The advance of Large Language Models (LLMs) has greatly stimulated research interest in developing multi-modal LLM (MLLM)-based visual anomaly detection (VAD) algorithms that can be deployed in complex environments. The challenge is that in these complex environments, the anomalies are sometimes highly contextual and also ambiguous, and thereby, uncertainty quantification (UQ) is a crucial capacity for an MLLM-based VAD system to succeed. In this paper, we introduce our UQ-supported MLLM-based VAD framework called ALARM. ALARM integrates UQ with quality-assurance techniques like reasoning chain, self-reflection, and MLLM ensemble for robust and accurate performance and is designed based on a rigorous probabilistic inference pipeline and computational process. Extensive empirical evaluations are conducted using the real-world smart-home benchmark data and wound image classification data, which shows ALARM's superior performance and its generic applicability across different domains for reliable decision-making.

Key facts. Cited by 2 papers in the map (data through 14 Oct 2026). Placed in Chart understanding and anomaly detection, one of 16 directions in Multimodal LLMs / vision-language models. Builds on 39 of its 76 references that are in the map. First posted on arXiv 1 Dec 2025.

Builds on

39 of 76 references.

Closest ancestors · 2

Same direction, newest first

  1. 2024Holmes-VAD: Towards Unbiased and Explainable Video Anomaly Detection via Multi-modal LLM18 Jun
  2. 2024Do LLMs Understand Visual Anomalies? Uncovering LLM's Capabilities in Zero-shot Anomaly Detection15 Apr

Other references · 37

  1. 2022Self-Consistency Improves Chain of Thought Reasoning in Language Modelscited by 5,708
  2. 2023Llama Guard: LLM-based Input-Output Safeguard for Human-AI Conversationscited by 1,207
  3. 2017Selective Classification for Deep Neural Networkscited by 852
  4. 2019Memorizing Normality to Detect Anomaly: Memory-augmented Deep Autoencoder for Unsupervised Anomaly Detectioncited by 564
  5. 2020Classification with Valid and Adaptive Coveragecited by 396
  6. 2017Future Frame Prediction for Anomaly Detection -- A New Baselinecited by 391
  7. 2019SelectiveNet: A Deep Neural Network with an Integrated Reject Optioncited by 350
  8. 2024R-Judge: Benchmarking Safety Risk Awareness for LLM Agentscited by 288
  9. 2016Least Ambiguous Set-Valued Classifiers with Bounded Error Levelscited by 272
  10. 2016Learning Temporal Regularity in Video Sequencescited by 254
  11. 2017Predict Responsibly: Improving Fairness and Accuracy by Learning to Defercited by 233
  12. 2021Weakly-supervised Video Anomaly Detection with Robust Temporal Feature Magnitude Learningcited by 230
25 more
  1. 2024Kernel Language Entropy: Fine-grained Uncertainty Quantification for LLMs from Semantic Similaritiescited by 159
  2. 2023Quantifying Uncertainty in Answers from any Language Model and Enhancing their Trustworthinesscited by 122
  3. 2023Decomposing Uncertainty for Large Language Models through Input Clarification Ensemblingcited by 114
  4. 2018Object-centric Auto-encoders and Dummy Anomalies for Abnormal Event Detection in Videocited by 111
  5. 2019Graph Embedded Pose Clustering for Anomaly Detectioncited by 95
  6. 2021Learning Normal Dynamics in Videos with Meta Prototype Networkcited by 71
  7. 2021Optimal strategies for reject option classifierscited by 61
  8. 2024Video Anomaly Detection and Explanation via Large Language Modelscited by 47
  9. 2018An overview of deep learning based methods for unsupervised and semi-supervised anomaly detection in videoscited by 45
  10. 2024Uncertainty Quantification for In-Context Learning of Large Language Modelscited by 45
  11. 2025Position: Uncertainty Quantification Needs Reassessment for Large-language Model Agentscited by 32
  12. 2024LLM Uncertainty Quantification through Directional Entailment Graph and Claim Level Response Augmentationcited by 23
  13. 2025ER-Reason: A Benchmark Dataset for LLM Clinical Reasoning in the Emergency Roomcited by 22
  14. 2024Customizing Visual-Language Foundation Models for Multi-modal Anomaly Detection and Reasoningcited by 20
  15. 2024VANE-Bench: Video Anomaly Evaluation Benchmark for Conversational LMMscited by 20
  16. 2024LogiCode: an LLM-Driven Framework for Logical Anomaly Detectioncited by 19
  17. 2025Uncertainty Quantification of Large Language Models through Multi-Dimensional Responsescited by 18
  18. 2020Video Anomaly Detection for Smart Surveillancecited by 16
  19. 2019Transfer Learning for Non-Intrusive Load Monitoringcited by 14
  20. 2021Deep Video Anomaly Detection: Opportunities and Challengescited by 14
  21. 2024VisionGPT: LLM-Assisted Real-Time Anomaly Detection for Safe Visual Navigationcited by 14
  22. 2025Autonomous Control Leveraging LLMs: An Agentic Framework for Next-Generation Industrial Automationcited by 8
  23. 2025VAGU & GtS: LLM-Based Benchmark and Framework for Joint Video Anomaly Grounding and Understandingcited by 8
  24. 2025Inv-Entropy: A Fully Probabilistic Framework for Uncertainty Quantification in Language Modelscited by 6
  25. 2024An AI-Based System Utilizing IoT-Enabled Ambient Sensors and LLMs for Complex Activity Trackingcited by 5

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2026: 2.

2 papers.

  1. 2026Team, Then Trim: An Assembly-Line LLM Framework for High-Quality Tabular Data Generationcited by 1
  2. 2026A Role-Based LLM Framework for Structured Information Extraction from Healthy Food Policiescited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2024Quo Vadis, Anomaly Detection? LLMs and VLMs in the Spotlight
  2. 2025The Evolution of Video Anomaly Detection: A Unified Framework from DNN to MLLM
  3. 2025LogicAD: Explainable Anomaly Detection via VLM-based Text Feature Extraction
  4. 2026Advancing Adaptive Multi-Stage Video Anomaly Reasoning: A Benchmark Dataset and Method
  5. 2025Vad-R1: Towards Video Anomaly Reasoning via Perception-to-Cognition Chain-of-Thought
  6. 2026Tiny but Trusted: Efficient Vision-Language Reasoning for Time-Series Anomaly Detection
  7. 2024Video Anomaly Detection in 10 Years: A Survey and Outlook
  8. 2025SmartHome-Bench: A Comprehensive Benchmark for Video Anomaly Detection in Smart Homes Using Multi-Modal Large Language Models