通过背景区 anthology 为语言模型构建虚拟人物
Virtual Personas for Language Models via an Anthology of Backstories
AI总结：
本文提出 anthology 方法，利用开放性生活叙述引导语言模型生成特定虚拟人物，提升实验结果的一致性和可靠性，通过三个人类调查发现其在匹配响应分布和一致性指标上分别提升18%和27%。
摘要：
大型语言模型（LLMs）从数百万不同作者的文本仓库中进行训练，反映了人类特征的巨大多样性。尽管这些模型有潜力作为行为研究中人类主体的近似，但先前的努力在引导模型响应以匹配个体人类用户方面受到限制。在本工作中，我们引入了
英文摘要：
Large language models (LLMs) are trained from vast repositories of text authored by millions of distinct authors, reflecting an enormous diversity of human traits. While these models bear the potential to be used as approximations of human subjects in behavioral studies, prior efforts have been limited in steering model responses to match individual human users. In this work, we introduce "Anthology", a method for conditioning LLMs to particular virtual personas by harnessing open-ended life narratives, which we refer to as "backstories." We show that our methodology enhances the consistency and reliability of experimental outcomes while ensuring better representation of diverse sub-populations. Across three nationally representative human surveys conducted as part of Pew Research Center's American Trends Panel (ATP), we demonstrate that Anthology achieves up to 18% improvement in matching the response distributions of human respondents and 27% improvement in consistency metrics.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
