{
  "id": 4570,
  "url": "https://arxiv.org/abs/2605.10267v3",
  "title": "IndustryBench: Probing the Industrial Knowledge Boundaries of LLMs",
  "summary": "In industrial procurement, an LLM answer is useful only if it survives a standards check: recommended material must match operating condition, every parameter must respect a regulated threshold, and no procedure may contradict a safety clause. Partial correctness can mask safety-critical contradictions that aggregate LLM benchmarks rarely capture. We introduce IndustryBench, a 2,049-item benchmark for industrial procurement QA in Chinese, grounded in Chinese national standards (GB/T) and structu",
  "authors": "Songlin Bai, Xintong Wang, Linlin Yu, Bin Chen, Zhiang Xu, Yuyang Sheng et al.",
  "category": "research",
  "topics": "regulation",
  "orgs": null,
  "regions": "china",
  "published_at": "2026-05-11T09:30:48.000Z",
  "fetched_at": "2026-07-14T16:31:08.353Z",
  "source_slug": "arxiv-ethics",
  "source_name": "arXiv",
  "source_homepage": "https://arxiv.org",
  "ethics_ai_record_url": "https://ethics.ai/record/4570",
  "original_url": "https://arxiv.org/abs/2605.10267v3",
  "evidence_status": "source-only",
  "attribution": "via ethics.ai"
}