{
  "id": 1445,
  "url": "https://arxiv.org/abs/2606.05792v1",
  "title": "Can LLMs Write Correct TLA+ Specifications? Evaluating Natural-Language-to-TLA+ Generation",
  "summary": "TLA+ has supported industrial verification at companies such as Amazon and Microsoft, yet writing correct TLA+ specifications from natural language still requires time and expertise, which limits adoption. LLMs show promise, but no prior study measures whether they produce semantically correct TLA+ specifications from natural language. This paper presents the first systematic evaluation of LLM-based TLA+ specification synthesis from natural language. Our study evaluates 30 LLMs across eight fami",
  "authors": "Arslan Bisharat, Brian Ortiz, Eric Spencer, Khushboo Bhadauria, TaiNing Wang, George K. Thiruvathukal et al.",
  "category": "research",
  "topics": null,
  "orgs": "microsoft,amazon",
  "regions": null,
  "published_at": "2026-06-04T07:22:01.000Z",
  "fetched_at": "2026-07-14T14:15:17.101Z",
  "source_slug": "arxiv-ethics",
  "source_name": "arXiv",
  "source_homepage": "https://arxiv.org",
  "ethics_ai_record_url": "https://ethics.ai/record/1445",
  "original_url": "https://arxiv.org/abs/2606.05792v1",
  "evidence_status": "source-only",
  "attribution": "via ethics.ai"
}