mlsanityData to 14 Oct 2026

Multimodal RAG-driven Anomaly Detection and Classification in Laser Powder Bed Fusion using Large Language Models

arXiv 2505.13828 ↗First posted 20 May 2025cs.AIcited by 3

Not on the map. Why?

Abstract (arXiv)

Additive manufacturing enables the fabrication of complex designs while minimizing waste, but faces challenges related to defects and process anomalies. This study presents a novel multimodal Retrieval-Augmented Generation-based framework that automates anomaly detection across various Additive Manufacturing processes leveraging retrieved information from literature, including images and descriptive text, rather than training datasets. This framework integrates text and image retrieval from scientific literature and multimodal generation models to perform zero-shot anomaly identification, classification, and explanation generation in a Laser Powder Bed Fusion setting. The proposed framework is evaluated on four L-PBF manufacturing datasets from Oak Ridge National Laboratory, featuring various printer makes, models, and materials. This evaluation demonstrates the framework's adaptability and generalizability across diverse images without requiring additional training. Comparative analysis using Qwen2-VL-2B and GPT-4o-mini as MLLM within the proposed framework highlights that GPT-4o-mini outperforms Qwen2-VL-2B and proportional random baseline in manufacturing anomalies classification. Additionally, the evaluation of the RAG system confirms that incorporating retrieval mechanisms improves average accuracy by 12% by reducing the risk of hallucination and providing additional information. The proposed framework can be continuously updated by integrating emerging research, allowing seamless adaptation to the evolving landscape of AM technologies. This scalable, automated, and zero-shot-capable framework streamlines AM anomaly analysis, enhancing efficiency and accuracy.

Key facts. Cited by 3 papers in the map (data through 14 Oct 2026). Builds on 27 of its 50 references that are in the map. First posted on arXiv 20 May 2025.

Builds on

27 of 50 references.

References · 27

  1. 2021Learning Transferable Visual Models From Natural Language Supervisioncited by 33,744
  2. 2024Qwen2-VL: Enhancing Vision-Language Model's Perception of the World at Any Resolutioncited by 4,234
  3. 2023WinCLIP: Zero-/Few-Shot Anomaly Classification and Segmentationcited by 315
  4. 2023AnomalyCLIP: Object-agnostic Prompt Learning for Zero-shot Anomaly Detectioncited by 271
  5. 2024VisRAG: Vision-based Retrieval-augmented Generation on Multi-modality Documentscited by 245
  6. 2024ColPali: Efficient Document Retrieval with Vision Language Modelscited by 195
  7. 2023AnomalyGPT: Detecting Industrial Anomalies Using Large Vision-Language Modelscited by 171
  8. 2019Towards Knowledge-Based Recommender Dialog Systemcited by 113
  9. 2025Towards Zero-Shot Anomaly Detection and Reasoning with Multimodal Large Language Modelscited by 54
  10. 2024ClipSAM: CLIP and SAM Collaboration for Zero-Shot Anomaly Segmentationcited by 49
  11. 2024MMAD: A Comprehensive Benchmark for Multimodal Large Language Models in Industrial Anomaly Detectioncited by 47
  12. 2023Towards LLM-guided Causal Explainability for Black-box Text Classifierscited by 44
15 more
  1. 2023Myriad: Large Multimodal Model by Applying Vision Experts for Industrial Anomaly Detectioncited by 39
  2. 2024DesignQA: A Multimodal Benchmark for Evaluating Large Language Models' Understanding of Engineering Documentationcited by 32
  3. 2024How Much Can RAG Help the Reasoning of LLM?cited by 31
  4. 2024AD-LLM: Benchmarking Large Language Models for Anomaly Detectioncited by 26
  5. 2024M3DM-NR: RGB-3D Noisy-Resistant Industrial Anomaly Detection via Multimodal Denoisingcited by 24
  6. 2024AMGPT: a Large Language Model for Contextual Querying in Additive Manufacturingcited by 23
  7. 2024LLM-3D Print: Large Language Models To Monitor and Control 3D Printingcited by 18
  8. 2024VMAD: Visual-enhanced Multimodal Large Language Model for Zero-Shot Anomaly Detectioncited by 13
  9. 2024FabGPT: An Efficient Large Multimodal Model for Complex Wafer Defect Knowledge Queriescited by 12
  10. 2025KAnoCLIP: Zero-Shot Anomaly Detection through Knowledge-Driven Prompt Learning and Enhanced Cross-Modal Integrationcited by 7
  11. 2025AdditiveLLM: Large Language Models Predict Defects in Additive Manufacturingcited by 5
  12. 2024FDM-Bench: A Comprehensive Benchmark for Evaluating Large Language Models in Additive Manufacturing Taskscited by 4
  13. 2025Large Language Models for Extrapolative Modeling of Manufacturing Processescited by 4
  14. 2025RAAD-LLM: Adaptive Anomaly Detection Using LLMs and RAG Integrationcited by 4
  15. 2024Keyword-driven Retrieval-Augmented Large Language Models for Cold-start User Recommendationscited by 3

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2026: 3.

3 papers.

  1. 2026MCERF: Advancing Multimodal LLM Evaluation of Engineering Documentation with Enhanced Retrievalcited by 2
  2. 2026Task-Aware Scanning Parameter Configuration for Robotic Inspection Using Vision Language Embeddings and Hyperdimensional Computingcited by 1
  3. 2026LLM-ADAM: A Generalizable LLM Agent Framework for Pre-Print Anomaly Detection in Additive Manufacturingcited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2026Towards Agentic Defect Reasoning: A Graph-Assisted Retrieval Framework for Laser Powder Bed Fusion
  2. 2025In-Context-Learning-Assisted Quality Assessment Vision-Language Models for Metal Additive Manufacturing
  3. 2025Towards Open-Vocabulary Industrial Defect Understanding with a Large-Scale Multimodal Dataset
  4. 2025QA-VLM: Providing human-interpretable quality assessment for wire-feed laser additive manufacturing parts with Vision Language Models
  5. 2024Deep Reinforcement Learning Based Toolpath Generation for Thermal Uniformity in Laser Powder Bed Fusion Process
  6. 2026A Knowledge-Driven LLM-Based Decision-Support System for Explainable Defect Analysis and Mitigation Guidance in Laser Powder Bed Fusion
  7. 2023Inexpensive High Fidelity Melt Pool Models in Additive Manufacturing Using Generative Deep Diffusion
  8. 2026Multi-Head Attention-Based Feature Extractor Integration with Soft Actor-Critic for Porosity Prediction and Process Parameter Optimization in Additive Manufacturing