Review
Jul 2026
When Synthetic Users Fail: A Cross-Domain Benchmark of LLM-Simulated Human Survey Responses
The cross-domain benchmark and the evaluation framework for intelligent synthetic-user evidence is made available on request, so that teams can determine in advance when synthetic-user evidence is safe for decision support and when it is not.
Zihang Chen, Di Zhu, L. Zheng
· arXiv.org · 2 citations