研究生成式代理对提示词的敏感性，发现微小变化会影响行为结果。
Prompt Sensitivity of Generative Agents: Evidence from an Epidemic Model
- 用每日提示决定隔离或社交，构建生成式代理疫情模型。
- 同义提示几乎不改变疫情结果，但细微差异会引发行为变化。
- 角色名称对疫情传播影响不大，适合模拟人类行为的研究者参考。
随着生成式AI广泛应用，研究者正探索其作为人类代理的潜力。生成式代理（由生成式AI驱动）在认知心理学实验和疫情模拟中能产生真实的人类行为。本研究通过生成式代理疫情模型，每日向每个代理发送提示，判断其是否选择隔离或与他人接触，考察提示修改和角色名称变化对其行为的影响。结果显示，使用同义提示时，模型结果几乎无变化；但提示的微小差异及上下文变动会显著影响模型输出。此外，不同角色名称（特别是带有特定人格设定的名称）对疫情传播结果无明显影响。
原文摘要 · Abstract (English)
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.
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。