arXiv：cs.AI· Khashayar Pourtaheri, Ahmad Zareei·· 16 小时前
用行为历史而非人物描述提升 LLM 合成人物预测个体选择的能力
Behavioral History Outperforms Descriptions of the Person for LLM Synthetic Personas
AI 导读
一项基于 845 名美国成年人两波面板数据的研究显示，LLM 合成人物若要预测个体后续选择，提供受访者此前的问卷作答（行为历史）比提供人口统计、人格特质或认知分数更有效。仅靠描述的人物只能复原 53-67% 的人际差异，个体预测信息量仅为人类重测的 7-12%，加入行为历史后提升至 28%。含行为历史的条件下全部 17 个人口统计群体的估计信息量均为最高。
正文
Abstract:Large language models (LLMs) are increasingly used as synthetic personas representing survey respondents. Their validity as substitutes for particular respondents depends on whether they reproduce individuals' decisions. We examine what information helps synthetic respondents predict each individual's later choices, using five conditions that add progressively richer information: no personal information, demographics, personality traits, cognitive scores, and finally the respondent's earlier survey choices as behavioral history. We use a two-wave panel of 845 US adults who completed measures of 14 behavioral biases (spanning risk, time preferences, overconfidence, and reasoning), so each respondent's earlier answers provide a human test-retest benchmark; in the behavioral-history condition, all items that score the target bias are withheld. At the population level, the average number of biases per respondent in every condition is close to the human average (7.1-8.1 biases, against 7.1 for humans). This aggregate similarity masks differences in variance: persona descriptions recover only 53-67% of human between-person variation, whereas adding behavioral history restores it to approximately the human level. At the individual level, description-based personas achieve only 7-12% of the informedness observed in human test-retest responses, while adding behavioral history raises this to 28%. The condition including behavioral history has the highest estimated informedness in all 17 demographic groups, whereas description-based conditions provide little or no information for some groups. Synthetic responses also exhibit stronger education- and income-related differences than human responses. For LLM synthetic personas, a respondent's past answers add more to individual-level prediction than a description of who they are.
| Subjects: | Artificial Intelligence (cs.AI); Computation and Language (cs.CL); Computers and Society (cs.CY) |
| ACM classes: | I.2.7; J.4 |
| Cite as: | arXiv:2610.03998 [cs.AI] |
| (or arXiv:2610.03998v2 [cs.AI] for this version) | |
| https://doi.org/10.48550/arXiv.2610.03998 arXiv-issued DOI via DataCite |
Submission history
From: Khashayar Pourtaheri [view email]
[v1]
Fri, 2 Oct 2026 20:01:38 UTC (153 KB)
[v2]
Mon, 12 Oct 2026 23:48:42 UTC (124 KB)
来源：arXiv：cs.AI · arxiv.org