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

arXiv: https://arxiv.org/abs/2505.17615 · HTML: https://mlsanity.com/paper/2505.17615/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 23 of its 39 references that are in the map.
- First posted on arXiv 23 May 2025.

## Builds on (most cited first, 23 of 23)

- [Language Models are Few-Shot Learners](https://mlsanity.com/paper/2005.14165/) (2020)
- [Generative Agents: Interactive Simulacra of Human Behavior](https://mlsanity.com/paper/2304.03442/) (2023)
- [Deep Learning with Differential Privacy](https://mlsanity.com/paper/1607.00133/) (2016)
- [Membership Inference Attacks against Machine Learning Models](https://mlsanity.com/paper/1610.05820/) (2016)
- [BERT4Rec: Sequential Recommendation with Bidirectional Encoder Representations from Transformer](https://mlsanity.com/paper/1904.06690/) (2019)
- [Prompt Programming for Large Language Models: Beyond the Few-Shot Paradigm](https://mlsanity.com/paper/2102.07350/) (2021)
- [DiffuSeq: Sequence to Sequence Text Generation with Diffusion Models](https://mlsanity.com/paper/2210.08933/) (2022)
- [SeqGAN: Sequence Generative Adversarial Nets with Policy Gradient](https://mlsanity.com/paper/1609.05473/) (2016)
- [On LLMs-Driven Synthetic Data Generation, Curation, and Evaluation: A Survey](https://mlsanity.com/paper/2406.15126/) (2024)
- [Large Language Model as Attributed Training Data Generator: A Tale of Diversity and Bias](https://mlsanity.com/paper/2306.15895/) (2023)
- [AnnoLLM: Making Large Language Models to Be Better Crowdsourced Annotators](https://mlsanity.com/paper/2303.16854/) (2023)
- [Understanding World or Predicting Future? A Comprehensive Survey of World Models](https://mlsanity.com/paper/2411.14499/) (2024)
- [Large Language Models as Urban Residents: An LLM Agent Framework for Personal Mobility Generation](https://mlsanity.com/paper/2402.14744/) (2024)
- [AutoDebias: Learning to Debias for Recommendation](https://mlsanity.com/paper/2105.04170/) (2021)
- [Simplify and Robustify Negative Sampling for Implicit Collaborative Filtering](https://mlsanity.com/paper/2009.03376/) (2020)
- [A Survey of Large Language Model Empowered Agents for Recommendation and Search: Towards Next-Generation Information Retrieval](https://mlsanity.com/paper/2503.05659/) (2025)
- [Using Sequences of Life-events to Predict Human Lives](https://mlsanity.com/paper/2306.03009/) (2023)
- [Mixture of Soft Prompts for Controllable Data Generation](https://mlsanity.com/paper/2303.01580/) (2023)
- [Be More Real: Travel Diary Generation Using LLM Agents and Individual Profiles](https://mlsanity.com/paper/2407.18932/) (2024)
- [Privacy-Preserving Synthetic Data Generation for Recommendation Systems](https://mlsanity.com/paper/2209.13133/) (2022)
- [Improving the Sample Efficiency of Prompt Tuning with Domain Adaptation](https://mlsanity.com/paper/2210.02952/) (2022)
- [A Population-to-individual Tuning Framework for Adapting Pretrained LM to On-device User Intent Prediction](https://mlsanity.com/paper/2408.09815/) (2024)
- [Intelligent Virtual Assistant knows Your Life](https://mlsanity.com/paper/1803.00466/) (2018)

## Abstract (arXiv)

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.