用真实社交数据生成高保真虚拟人物，支持大规模社会模拟。
Synthia: Scalable Grounded Persona Generation from Social Media Data
- 用真实社交帖子约束大模型生成人物，保证真实性。
- 在多个测评中更贴近人类观点分布，且模型更小。
- 保留真实社交网络结构，适合研究群体同质性等问题。
基于角色的仿真在计算社会科学中应用日益广泛，但其有效性关键取决于角色的真实程度。构建既真实又可扩展的虚拟人群仍是核心挑战。我们提出 Synthia，一个将大模型生成的角色与真实社交平台（Bluesky）公开帖子相结合的人格生成框架，利用真实数据锚定角色特征，由语言模型完成叙事构造。在多个社会调查基准测试中，Synthia 在人类观点分布对齐方面优于现有最优方法，且使用更小的模型。多维度公平性与偏见分析显示，对多数人口统计学群体在不同维度上均表现更优。独特之处在于，Synthia 保持了基于真实社交用户的人物间交互图结构，支持网络感知分析，我们在两个聚焦同质性的案例研究中予以验证。这些结果表明，Synthia 是构建可扩展、高保真、公平虚拟人群的实用可靠框架。
原文摘要 · Abstract (English)
Persona-driven simulations are increasingly used in computational social science, yet their validity critically depends on the fidelity of the underlying personas. Constructing virtual populations that are both authentic and scalable remains a central challenge. We introduce Synthia, a persona-generation framework that grounds LLM-generated personas in real social-media posts while delegating narrative construction to language models, using publicly available data from the Bluesky platform. Across multiple social-survey benchmarks, Synthia improves alignment with human opinion distributions over prior state-of-the-art approaches while relying on substantially smaller models. A multi-dimensional fairness and bias analysis shows that Synthia outperforms previous methods for most demographics across different dimensions. Uniquely, Synthia preserves interaction-graph structure among personas grounded in real social network users, enabling network-aware analysis, which we demonstrate through two homophily-focused case studies. Together, these results position Synthia as a practical and reliable framework for constructing scalable, high-fidelity, and equitable virtual populations.
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。