发表机构
Virginia Tech（弗吉尼亚理工大学）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
该研究借助生成式智能体流行病模型，探究生成式智能体的行为对提示修改和角色名称的敏感性，发现同义提示影响极小，提示微小变化或情境改变会影响结果，角色名称对流行病结果无显著影响。
AI 中文摘要
随着生成式AI的影响力不断扩大，研究人员正在探索其作为人类代理的潜力，从参与认知心理学实验到经历疫情，由生成式AI模型驱动的生成式智能体在接收到提示时会产生逼真的人类行为。本研究探讨这些生成式智能体的行为对提示修改及智能体不同角色名称的敏感性。为评估该敏感性，我们采用生成式智能体流行病模型，其中每个智能体每日都会收到关于是否要隔离或与其他智能体接触的提示。我们发现，使用同义提示会导致模型结果出现可忽略的变化；然而，提示的微小变化以及情境改变确实会影响模型结果。最后，我们的数据表明，分配给生成式智能体的不同角色名称（特别是那些被赋予角色的名称）不会显著影响流行病结果。
英文摘要
As generative AI gains traction, researchers are investigating its potential to serve as proxies for humans. From undergoing cognitive psychology experiments to experiencing an epidemic, generative agents, agents powered by generative AI models, produce realistic human behavior when prompted. This study explores the sensitivity of these generative agents' behavior to prompt modifications and varied persona names of the agents. To assess this sensitivity, we use a generative agent epidemic model, wherein each agent is prompted daily on whether it wants to isolate or commingle with other agents. We found that using synonymous prompts results in negligible changes to the model's outcomes. However, minor variations in prompts, as well as contextual changes, do influence the model's results. Lastly, our data indicates that different persona names assigned to generative agents, specifically those imbued with personas, do not significantly impact epidemic outcomes.
Comments14 pages, 3 figures. Code and data: https://github.com/RossFW/Paper2-Prompt-Sensitivity-of-Generative-Agents
