Procedural Knowledge Extraction from Industrial Troubleshooting Guides Using Vision Language Models

The paper examines how Vision Language Models (VLMs) can automatically extract structured procedural knowledge from industrial troubleshooting guides, which are typically flowchart-like diagrams combining spatial layout and technical language. It evaluates two VLMs using two prompting strategies—standard instruction-guided and an augmented approach that highlights layout patterns—and finds that each model shows different trade-offs between sensitivity to layout and robustness to semantic content. These insights help determine which VLM and prompting method is most suitable for integrating such guides into operator support systems.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv AI.

• llms