When prompt perturbations break your A/B test: A valid statistical test for generative surveying 文章

ArXiv CS.AI2026-05-28NEWSen作者: Hayden Helm, Carey Priebe
查看原文 →
关系图谱

When prompt perturbations break your A/B test: A valid statistical test for generative surveying · 相关技术

相关技术

LLMpermutation testWilcoxon signed-rank testsign test