arXiv cs.CL· Grace Jiarui Fan, Chengpiao Huang, Tianyi Peng, Kaizheng Wang, Yuhang Wu·· 12 小时前AI 评分31
SYN-DIGITS：面向数字孪生模拟校准的合成控制框架
SYN-DIGITS: A Synthetic Control Framework for Calibrated Digital Twin Simulation
AI 导读
SYN-DIGITS 是一个模型无关的后验校准框架，通过学习数字孪生中问题间的关系并迁移到人类侧，在无目标问题人类反馈的冷启动场景下预测人类回答。在三个数据集、十三种人格构建上，其个体级相关性相对提升 11% 至 417%，分布差异相对降低 46%–57%。该框架还支持仅有参考问题边际信息时的分布级校准。
正文 · 原文
Abstract:Persona simulation based on large language models---often referred to as digital twin simulation---is increasingly used for market research, recommender systems, and social science research. However, these simulations often exhibit systematic bias and miscalibration relative to real human behavior. We propose SYN-DIGITS, a model-agnostic, post-hoc calibration framework that learns relationships among questions from digital twins and transfers them to predict human responses. We focus on a cold-start setting in which no human response to the target question is observed, so calibration must rely on digital twins and human data on reference questions. Our analysis shows that, though digital twins may not reproduce individual human responses accurately, they can capture nontrivial relationships among questions that can be effectively transferred to the human side. When individual-level data is unavailable and we only have access to marginal information on reference questions, our framework also supports distribution-level calibration for predicting the distribution of human responses on the target question. Across three datasets and thirteen persona constructions, experiments show that SYN-DIGITS achieves 11% to 417% relative improvements in individual-level correlation and 46%--57% relative reductions in distributional discrepancy compared to uncalibrated baselines.
| Subjects: | Machine Learning (cs.LG); Artificial Intelligence (cs.AI); Computation and Language (cs.CL); Computers and Society (cs.CY) |
| Cite as: | arXiv:2604.07513 [cs.LG] |
| (or arXiv:2604.07513v2 [cs.LG] for this version) | |
| https://doi.org/10.48550/arXiv.2604.07513 arXiv-issued DOI via DataCite |
Submission history
From: Yuhang Wu [view email]
[v1]
Wed, 8 Apr 2026 18:50:01 UTC (237 KB)
[v2]
Sat, 31 Oct 2026 01:57:35 UTC (422 KB)
来源：arXiv cs.CL · arxiv.org