arXiv cs.CL· Iris Ye, Tianze Deng, Ozan Candogan·· 11 小时前AI 评分20
BDE 结构化问卷历史提升 LLM 数字孪生预测准确率：一项受控研究
Structuring Survey Histories for LLM Digital Twins: A Controlled Study of Background, Decision Procedure, and Evaluation Profiles
AI 导读
研究提出 BDE 固定表示，将受访者问卷历史组织为 Background、Decision procedure 和 Evaluation 三部分，在 Twin-2K-500 的 17 项任务上预测留出答案。
正文 · 原文
Abstract:LLM-based digital twins aim to predict how individuals would respond in new settings from representations of their prior responses. Existing evidence that compression of survey histories need not reduce predictive accuracy suggests that representation structure, rather than information volume alone, may be an important design choice. We study BDE, a fixed representation that organizes each respondent's survey history into Background, Decision procedure, and Evaluation. We evaluate it on Twin-2K-500 (Toubia et al., 2025) by predicting each respondent's held-out answers on 17 tasks. In a paired evaluation with 100 respondents, a fully inferred BDE profile improves overall accuracy over the raw survey transcript by 1.27 percentage points (pp) on gpt-5.4-nano (p < 0.01) and 1.19 pp on gpt-5.4-mini (p < 0.001). Three analyses then examine the schema, extraction depth, and component composition. Against a length-matched free-form profile written from the same transcript by the same extractor, BDE improves pricing accuracy on both simulators (2.15 pp on nano, p < 0.01; 1.38 pp on mini, p < 0.05), while its overall advantage is significant only on nano (1.05 pp, p < 0.05). Allowing deeper inference during extraction yields no statistically significant gain on either simulator. By contrast, adding Evaluation to a Background--Decision procedure profile improves overall accuracy by 1.44 pp on nano (p < 0.001) and 1.22 pp on mini (p < 0.001). These results indicate that the advantage over raw transcripts is not explained by compression or length alone, and attribute it primarily to profile composition rather than deeper extraction.
| Comments: | 10 pages. Camera-ready version for SocialAgent: Second Workshop on Large Language Models for Social Reasoning and Simulation, NeurIPS 2026 |
| Subjects: | Computation and Language (cs.CL) |
| Cite as: | arXiv:2611.08730 [cs.CL] |
| (or arXiv:2611.08730v1 [cs.CL] for this version) | |
| https://doi.org/10.48550/arXiv.2611.08730 arXiv-issued DOI via DataCite (pending registration) |
Submission history
From: Tianze Deng Mr. [view email]
[v1]
Thu, 5 Nov 2026 21:25:46 UTC (20 KB)
来源：arXiv cs.CL · arxiv.org