<ul><li>Predicting human daily behavior is a complex task due to routine patterns and short-term fluctuations.</li><li>BehaviorGen is a framework introduced in this work that uses large language models (LLMs) to generate high-quality synthetic behavior data.</li><li>The framework supports data augmentation and replacement in behavior prediction models by simulating user behavior based on profiles and real events.</li><li>Evaluation of BehaviorGen shows significant improvements in human mobility and smartphone usage predictions, with gains of up to 18.9%.</li></ul>

Large language model as user daily behavior data generator: balancing population diversity and individual personality

Discover more