用大模型模拟人类行为，可为社科研究提供新方法。
LLM Social Simulations Are a Promising Research Method
- 通过上下文提示和社科数据微调提升模拟真实度
- 现有大模型已可用于初步探索性研究
- 适合社科与AI交叉研究者尝试新范式
大型语言模型对人类研究对象的准确、可验证模拟，有望成为理解人类行为和训练新AI系统的一种可及数据源。然而，目前成果有限，且少有社会科学家采用此方法。本文认为，通过解决五个可处理的挑战，这一潜力可被实现。我们基于对大模型与人类受试者实证比较、相关评论及文献的综述展开论证，提出包括上下文丰富提示和使用社会科学数据集微调等有前景的方向。我们认为，当前大模型模拟已可用于试点与探索性研究，随着大模型能力快速进步，更广泛应用或即将实现。研究者应优先发展概念模型与迭代评估，以充分发挥新AI系统潜力。
原文摘要 · Abstract (English)
Accurate and verifiable large language model (LLM) simulations of human research subjects promise an accessible data source for understanding human behavior and training new AI systems. However, results to date have been limited, and few social scientists have adopted this method. In this position paper, we argue that the promise of LLM social simulations can be achieved by addressing five tractable challenges. We ground our argument in a review of empirical comparisons between LLMs and human research subjects, commentaries on the topic, and related work. We identify promising directions, including context-rich prompting and fine-tuning with social science datasets. We believe that LLM social simulations can already be used for pilot and exploratory studies, and more widespread use may soon be possible with rapidly advancing LLM capabilities. Researchers should prioritize developing conceptual models and iterative evaluations to make the best use of new AI systems.
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。