在人类与AI共存系统中，通过群体构成差异识别人类的因果效应。
Causal Effects with Unobserved Unit Types in Interacting Human-AI Systems
- 基于人类-AI先验构建子群体，利用预期人类占比差异设计实验。
- 通过因果消息传递框架，实现对人类特异性因果效应的一致估计。
- 适用于无法观测个体类型或交互网络的新型人机协同系统实验。
我们研究人类与AI代理交互群体中的实验，其中单位类型和交互网络均不可观测。尽管因果效应在整个系统中传播，但目标是估计对人类的影响。例如在线平台中人类用户与由AI驱动的账号互动。假设一个人类-AI先验，每个单位具有成为人类的概率。虽然无法在个体层面区分人类，但该先验允许我们计算大规模子群体中的人类平均占比。随后，我们通过因果消息传递（CMP）框架建模结果动态，并分析各子群体的样本均值结果。我们证明，通过构造具有不同预期人类占比和处理暴露的子群体，可一致恢复人类特异性因果效应。研究揭示了仅依赖群体构成分布知识（无需观测个体类型或交互网络）即可实现识别的条件。我们在一个由行为差异化的大语言模型代理驱动的模拟人机平台中验证了该方法。这些结果共同提供了新兴人机系统中实验设计的理论与实践框架。
原文摘要 · Abstract (English)
We study experiments on interacting populations of humans and AI agents, where both unit types and the interaction network remain unobserved. Although causal effects propagate throughout the system, the goal is to estimate effects on humans. Examples include online platforms where human users interact alongside AI-driven accounts. We assume a human-AI prior that gives each unit a probability of being human. While humans cannot be distinguished at the unit level, the prior allows us to compute the average human composition within large subpopulations. We then model outcome dynamics through a causal message passing (CMP) framework and analyze sample-mean outcomes across subpopulations. We show that by constructing subpopulations that vary in expected human composition and treatment exposure, one can consistently recover human-specific causal effects. Our results characterize when distributional knowledge of population composition (without observing unit types or the interaction network) is sufficient for identification. We validate the approach on a simulated human-AI platform driven by behaviorally differentiated LLM agents. Together, these results provide a theoretical and practical framework for experimentation in emerging human-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。