LLM生成的人物角色是一个暗藏陷阱的承诺
LLM Generated Persona is a Promise with a Catch
AI总结：
本研究指出当前LLM生成人物角色的启发式方法存在系统性偏差，通过美国选举预测和民意调查实验验证其与现实的显著偏离，提出需构建严谨的生成科学，并开源百万级人物角色数据集以支持后续研究。
摘要：
利用大语言模型（LLM）模拟人类行为已获得广泛关注，尤其是通过模拟个体特征的人物角色（persona）实现的模拟。基于人物角色的模拟有望变革依赖群体层面反馈的学科，包括社会科学、经济分析、营销研究和商业运营。传统的真实人物角色数据收集方法面临重大挑战：由于隐私限制，这类方法成本极高且后勤难度大，且往往无法捕捉多维度属性，尤其是主观特质。因此，使用LLM生成合成人物角色提供了一种可扩展、高性价比的替代方案。然而，当前方法依赖临时的启发式生成技术，无法保证方法学严谨性或模拟精度，会在下游任务中产生系统性偏差。通过包含美国总统选举预测和美国民众总体意见调查在内的大规模实验，我们揭示这些偏差可能导致与现实结果的显著偏离。我们的研究结果强调了构建严谨的人物角色生成科学的必要性，并概述了提升LLM驱动的人物角色模拟的可靠性与可扩展性所需的方法学创新、组织与制度支持以及实证基础。为支持该领域的进一步研发，我们已开源约100万个生成的人物角色，可在https://huggingface.co/datasets/Tianyi-Lab/Personas 公开获取和分析。
英文摘要：
The use of large language models (LLMs) to simulate human behavior has gained significant attention, particularly through personas that approximate individual characteristics. Persona-based simulations hold promise for transforming disciplines that rely on population-level feedback, including social science, economic analysis, marketing research, and business operations. Traditional methods to collect realistic persona data face significant challenges. They are prohibitively expensive and logistically challenging due to privacy constraints, and often fail to capture multi-dimensional attributes, particularly subjective qualities. Consequently, synthetic persona generation with LLMs offers a scalable, cost-effective alternative. However, current approaches rely on ad hoc and heuristic generation techniques that do not guarantee methodological rigor or simulation precision, resulting in systematic biases in downstream tasks. Through extensive large-scale experiments including presidential election forecasts and general opinion surveys of the U.S. population, we reveal that these biases can lead to significant deviations from real-world outcomes. Our findings underscore the need to develop a rigorous science of persona generation and outline the methodological innovations, organizational and institutional support, and empirical foundations required to enhance the reliability and scalability of LLM-driven persona simulations. To support further research and development in this area, we have open-sourced approximately one million generated personas, available for public access and analysis at https://huggingface.co/datasets/Tianyi-Lab/Personas.
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。
