本頁只刊出中文翻譯與中文說明；英文原文請見下方原文連結。
原文連結
論文資訊
- 類型：已發表論文
- 日期：2025-06-02
摘要
Large 語言 models (LLMs), through their exposure to massive collections of online text, learn to reproduce the perspectives and linguistic styles of diverse 社會 and 文化 groups. This capability suggests a powerful 社會 scientific application-the simulation of empirically realistic, 文化ly situated human subjects. Synthesizing recent research in 人工智慧 and 計算 社會 science, we outline a methodological foundation for simulating human subjects and their 社會 interactions. We then identify six characteristics of current models that are likely to impair the realistic simulation of human subjects: bias, uniformity, atemporality, disembodiment, linguistic cultures, and alien intelligence. For each of these areas, we discuss promising approaches for overcoming their associated shortcomings. Given the rate of chan
※ 此為已發表論文，全文需透過期刊付費取得