LLM 结合人类数据设计个性化诱饵助推策略的研究
Integrating Large Language Models with Human Data to Design Personalized Decoy Nudges
AI 导读
一项预注册实地实验（3,495 名参与者、五个国家）测试用大语言模型（LLM）设计个性化诱 decoy 助推策略。结果显示，LLM 识别的国家最优诱饵参数在美国产生更强助推效果，德国边际显著，但在中国、印度、新加坡无效；LLM 个性化诱饵并不优于国家级最优诱饵。LLM 生成数据可作为贝叶斯选择模型的先验，在同等预测性能下将人类样本量需求估计减少 37-75%。
正文 · 原文
Abstract:Although nudge strategies can influence behavior, their effectiveness varies across individuals, highlighting the need for personalized nudge design. We hypothesize that large language models (LLMs) can facilitate the development of individual-specific nudges while reducing the financial and time costs associated with human data collection by augmenting small human samples or by replacing human participants. Using the decoy effect as a test case, we evaluate these hypotheses in a preregistered field experiment involving 3,495 participants across five countries. We show that decoy parameters identified by LLMs as optimal for a given country generate stronger nudging effects than non-optimal parameters in the United States and, marginally, in Germany, but not in China, India, or Singapore. We find no evidence that LLM-informed personalized decoys produce a stronger nudging effect than country-level optimal decoys. Finally, we demonstrate that LLM-generated data can serve as informative priors for Bayesian choice models, improving predictive performance and parameter estimation with smaller human samples. At matched predictive performance, this approach yields estimated reductions of 37-75$\%$ in human sample size. Overall, our findings suggest that LLMs hold considerable promise as low-cost tools for piloting and optimizing personalized nudge strategies, particularly when complemented with a small sample of human participants.
| Subjects: | Computers and Society (cs.CY); Artificial Intelligence (cs.AI) |
| Cite as: | arXiv:2508.12045 [cs.CY] |
| (or arXiv:2508.12045v3 [cs.CY] for this version) | |
| https://doi.org/10.48550/arXiv.2508.12045 arXiv-issued DOI via DataCite |
Submission history
From: Vladimir Maksimenko [view email]
[v1]
Sat, 16 Aug 2025 13:40:44 UTC (5,606 KB)
[v2]
Thu, 16 Oct 2025 12:33:13 UTC (2,477 KB)
[v3]
Sat, 24 Oct 2026 12:47:17 UTC (2,507 KB)
来源：arXiv cs.AI · arxiv.org