SafeBuild-Bench: A Temporal-Robust Construction Safety Benchmark with Graph-Enhanced Data Mining
Construction-safety models must handle concrete deployment risks, such as a worker standing near a scaffold edge without guardrails, rather than only recognize common objects in curated images. Yet real inspection archives are redundant, long-tailed, and collected across changing sites and months. We introduce SafeBuild-Bench, a metadata-driven benchmark for evaluating multimodal large language models on construction safety under realistic temporal and site variation. It is mined from 100K+ industrial image-text records and contains 3,314 task instances from over 3,000 expert-verified images, covering multiple-choice hazard identification and free-form hazard description. To make expert v...
| Authors | Yi Cui, Zilin Wang, Yijie Xu et al. |
|---|---|
| Primary category | cs.CV |
| Published | 29 July 2026 |
| Last updated at source | 29 July 2026 |
Connected in the knowledge graph
- peter23333/SafeBuild-BenchDataset · cited by
Models and datasets referencing this paper
- peter23333/SafeBuild-BenchDataset
Silytics shows public metadata from arXiv and links to the original. Information may be incomplete or out of date. Last refreshed 17 October 2026. Licenses and terms of the original apply to the work itself. Not financial, legal or professional advice.