合成人物预测真实受众？无人物基线反超人物模拟
原标题：Do Synthetic Personas Predict Real Audience Response? A Sim-to-Real Study Where a No-Persona Baseline Beats Persona-Based Copy Simulation
AI 摘要
该研究利用 Upworthy Research Archive 的真实标题 A/B 测试数据，检验 LLM 合成人物（synthetic personas）能否预测真实受众点击行为。结果发现，大多数 A/B 测试本身没有统计上可区分的胜者，而基于人物条件的预测反而比无人物零样本基线更差：无人物基线排名更准（top-1 准确率 49.2% vs 34.6%），且该结论在多个数据集和模型上稳健。作者结论是，预测总体参与度时，直接询问 LLM 比强制角色扮演更有效，合成人物不仅预测力弱，甚至不如不用。
正文节选
Do Synthetic Personas Predict Real Audience Response? A Sim-to-Real Study Where a No-Persona Baseline Beats Persona-Based Copy Simulation Abstract Marketers increasingly use large language models (LLMs) as “synthetic personas” to predict how an audience will react to a piece of copy before it ships, encouraged by evidence that profile-conditioned LLMs mimic human samples. But is that prediction actually valid against real behaviour—and does the persona machinery help? We present a sim-to-real va