大型语言模型作为用户日常行为数据生成器：平衡群体多样性与个体个性
Large language model as user daily behavior data generator: balancing population diversity and individual personality
AI总结：
针对日常行为预测中的数据隐私与可用性问题，提出BehaviorGen框架，利用大型语言模型生成合成行为数据，兼顾群体多样性与个体个性，在移动性和手机使用预测中最高提升18.9%。
摘要：
预测人类日常行为具有挑战性，因为常规模式与短期波动的复杂性。虽然数据驱动模型通过利用来自各种平台和设备的经验数据改进了行为预测，但对敏感的大规模用户数据的依赖引发了隐私问题并限制了数据可用性。合成数据生成已成为一种有前景的解决方案，尽管现有方法通常局限于特定应用。在本工作中，我们引入BehaviorGen，一个使用大型语言模型（LLMs）生成高质量合成行为数据的框架。通过基于用户画像和真实事件模拟用户行为，BehaviorGen支持行为预测模型中的数据增强和数据替换。我们在预训练增强、微调替换和微调增强等场景中评估其性能，在人类移动性和智能手机使用预测中取得了显著改进，增益高达18.9%。我们的结果证明了BehaviorGen通过灵活且保护隐私的合成数据生成来增强用户行为建模的潜力。
英文摘要：
Predicting human daily behavior is challenging due to the complexity of routine patterns and short-term fluctuations. While data-driven models have improved behavior prediction by leveraging empirical data from various platforms and devices, the reliance on sensitive, large-scale user data raises privacy concerns and limits data availability. Synthetic data generation has emerged as a promising solution, though existing methods are often limited to specific applications. In this work, we introduce BehaviorGen, a framework that uses large language models (LLMs) to generate high-quality synthetic behavior data. By simulating user behavior based on profiles and real events, BehaviorGen supports data augmentation and replacement in behavior prediction models. We evaluate its performance in scenarios such as pertaining augmentation, fine-tuning replacement, and fine-tuning augmentation, achieving significant improvements in human mobility and smartphone usage predictions, with gains of up to 18.9%. Our results demonstrate the potential of BehaviorGen to enhance user behavior modeling through flexible and privacy-preserving synthetic data generation.
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。
