发表机构
Columbia University（哥伦比亚大学）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
研究用GPT-4.1测试角色模拟在观点预测中的有效性，利用相关数据集进行实验，在选举结果和医学观点预测上取得一定成果，生成对话符合角色特点，解决偏差后角色模拟在多领域观点分析等应用前景广阔。
AI 中文摘要
角色模拟利用大语言模型根据特定特征信息预测人类选择或互动。为进一步了解当前局限性和未来方向，我们用GPT-4.1（知识截止到2024年6月）测试其在观点预测中的表现。利用哥伦比亚大学角色数据集的九个美国州的角色，GPT-4.1准确预测了九个州中八个州的2024年选举结果，仅在一个摇摆州失败。在医学和医疗保健观点方面，利用皮尤研究中心的数据集，GPT-4.1预测儿童疫苗信念的准确率高达0.94。应用GPT-4.1生成角色间对话，模拟对话和观点虽缺乏自然流畅性，但符合角色性格和背景。只要解决偏差问题，角色模拟是人工智能的一个有前途的应用，未来应用于多领域观点分析和反应预测将有益。
英文摘要
Persona simulation involves utilizing large language models (LLMs) to anticipate human choices or interactions based on specific characteristic information. To further understand current limitations and future directions, we tested persona simulation in opinion prediction with GPT-4.1 (knowledge cutoff by June 2024). Using personas from nine U.S. states provided by Columbia University's Personas dataset, GPT-4.1 accurately predicted 2024 election outcomes in eight out of the nine states, only failing in one of the swing states. We then focused on opinions related to medicine and healthcare. With the American Trends Panel Wave 123 dataset from Pew Research Center, GPT-4.1 was able to anticipate beliefs about childhood vaccines with an accuracy of up to 0.94. Furthermore, we applied GPT-4.1 to generate conversations among personas and observed that the simulated dialogues and opinions adhered well to personas' personalities and backgrounds, albeit lacking natural human-like flow. Persona simulation proves to be a promising application of artificial intelligence as long as biases are addressed. In the near future, it will be beneficial to apply it to opinion analysis and reaction prediction in diverse fields ranging from public health to lawmaking to economics.
CommentsICDM 2025 Undergraduate and High School Symposium
Journal refProceedings of the 2025 IEEE International Conference on Data Mining Workshops (ICDMW), pp. 2938-2942
DOI：10.1109/ICDMW69685.2025.00377
