{
  "id": 14831,
  "url": "https://arxiv.org/abs/2607.26348v1",
  "title": "When Synthetic Users Fail: A Cross-Domain Benchmark of LLM-Simulated Human Survey Responses",
  "summary": "Large language models (LLMs) are increasingly used as synthetic users, stand-ins for human respondents whose simulated answers feed product, policy, and market decisions. We ask when this substitution is valid and when it fails, and package the answer as an evaluation framework for intelligent synthetic-user systems. A single protocol, run across four models spanning two families and an 8B-to-frontier capability range, is applied to two independent domains of real human-response data: U.S. gener",
  "authors": "Zihan Chen, Di Zhu, Lei Nico Zheng",
  "category": "research",
  "topics": "regulation",
  "orgs": null,
  "regions": null,
  "published_at": "2026-07-28T23:43:00.000Z",
  "fetched_at": "2026-07-30T05:10:24.387Z",
  "source_slug": "x-arxiv-cs-hc",
  "source_name": "arXiv cs.HC",
  "source_homepage": "https://arxiv.org/list/cs.HC/recent",
  "ethics_ai_record_url": "https://ethics.ai/record/14831",
  "original_url": "https://arxiv.org/abs/2607.26348v1",
  "evidence_status": "source-only",
  "attribution": "via ethics.ai"
}