用大模型模拟社会行为需谨慎，避免误判为真实推断。
Evaluating the Use of Large Language Models as Synthetic Social Agents in Social Science Research
- 将大模型视为在限定条件下的模式匹配器，而非真实概率推断工具。
- 提出独立采样、预注册人类基线等实用防护措施。
- 适合社会科学研究中的快速原型设计与预测测试。
大语言模型正被广泛用于社会科学中的合成代理，涵盖问卷补全到多智能体仿真。本文警示研究者在解读模型输出时需保持审慎，并建议将其重新定位为在明确范围条件下进行准预测插值的高容量模式匹配器，而非概率推断替代品。文中提出一系列实践性防护机制，包括独立采样、预注册人类基线、可靠性感知验证和子群体校准，使研究者能在避免类别错误的前提下，有效开展原型设计与预测分析。
原文摘要 · Abstract (English)
Large Language Models (LLMs) are being increasingly used as synthetic agents in social science, in applications ranging from augmenting survey responses to powering multi-agent simulations. This paper outlines cautions that should be taken when interpreting LLM outputs and proposes a pragmatic reframing for the social sciences in which LLMs are used as high-capacity pattern matchers for quasi-predictive interpolation under explicit scope conditions and not as substitutes for probabilistic inference. Practical guardrails such as independent draws, preregistered human baselines, reliability-aware validation, and subgroup calibration, are introduced so that researchers may engage in useful prototyping and forecasting while avoiding category errors.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。