{
  "id": 5861,
  "url": "https://arxiv.org/abs/2604.12995v1",
  "title": "PolicyLLM: Towards Excellent Comprehension of Public Policy for Large Language Models",
  "summary": "Large Language Models (LLMs) are increasingly integrated into real-world decision-making, including in the domain of public policy. Yet, their ability to comprehend and reason about policy-related content remains underexplored. To fill this gap, we present \\textbf{\\textit{PolicyBench}}, the first large-scale cross-system benchmark (US-China) evaluating policy comprehension, comprising 21K cases across a broad spectrum of policy areas, capturing the diversity and complexity of real-world governan",
  "authors": "Han Bao, Penghao Zhang, Yue Huang, Zhengqing Yuan, Yanchi Ru, Rui Su et al.",
  "category": "research",
  "topics": "regulation",
  "orgs": null,
  "regions": "china",
  "published_at": "2026-04-14T17:27:50.000Z",
  "fetched_at": "2026-07-14T16:32:02.062Z",
  "source_slug": "arxiv-ethics",
  "source_name": "arXiv",
  "source_homepage": "https://arxiv.org",
  "ethics_ai_record_url": "https://ethics.ai/record/5861",
  "original_url": "https://arxiv.org/abs/2604.12995v1",
  "evidence_status": "source-only",
  "attribution": "via ethics.ai"
}