{
  "id": 5273,
  "url": "https://arxiv.org/abs/2604.25359v1",
  "title": "The Structured Output Benchmark: A Multi-Source Benchmark for Evaluating Structured Output Quality in Large Language Models",
  "summary": "Large Language Models are increasingly being deployed to extract structured data from unstructured and semi-structured sources: parsing invoices, medical records, and converting PDF documents to database entries. Yet existing benchmarks for structured output generation either focus on schema compliance alone, or evaluate value correctness within a single source domain. We introduce SOB (The Structured Output Benchmark), a multi-source benchmark spanning three source modalities: native text, imag",
  "authors": "Abhinav Kumar Singh, Harsha Vardhan Khurdula, Yoeven D Khemlani, Vineet Agarwal",
  "category": "research",
  "topics": "regulation,healthcare",
  "orgs": null,
  "regions": null,
  "published_at": "2026-04-28T08:27:01.000Z",
  "fetched_at": "2026-07-14T16:31:40.217Z",
  "source_slug": "arxiv-ethics",
  "source_name": "arXiv",
  "source_homepage": "https://arxiv.org",
  "ethics_ai_record_url": "https://ethics.ai/record/5273",
  "original_url": "https://arxiv.org/abs/2604.25359v1",
  "evidence_status": "source-only",
  "attribution": "via ethics.ai"
}