Geo-Llama: Leveraging LLMs for Human Mobility Trajectory Generation with Spatiotemporal Constraints
This addresses a domain-specific problem for researchers in transportation, urban planning, and epidemic control by providing a controlled generation method, though it is incremental as it builds on existing LLM and trajectory generation approaches.
The paper tackles the problem of generating realistic human mobility trajectories with spatiotemporal constraints, introducing Geo-Llama, an LLM finetuning framework that effectively enforces multiple explicit visit constraints and demonstrates versatility and robustness in generating more realistic trajectories compared to existing methods.
Generating realistic human mobility data is essential for various application domains, including transportation, urban planning, and epidemic control, as real data is often inaccessible to researchers due to high costs and privacy concerns. Existing deep generative models learn from real trajectories to generate synthetic ones. Despite the progress, most of them suffer from training stability issues and scale poorly with increasing data size. More importantly, they often lack control mechanisms to guide the generated trajectories under constraints such as enforcing specific visits. To address these limitations, we formally define the controlled trajectory generation problem for effectively handling multiple spatiotemporal constraints. We introduce Geo-Llama, a novel LLM finetuning framework that can enforce multiple explicit visit constraints while maintaining contextual coherence of the generated trajectories. In this approach, pre-trained LLMs are fine-tuned on trajectory data with a visit-wise permutation strategy where each visit corresponds to a specific time and location. This strategy enables the model to capture spatiotemporal patterns regardless of visit orders while maintaining flexible and in-context constraint integration through prompts during generation. Extensive experiments on real-world and synthetic datasets validate the effectiveness of Geo-Llama, demonstrating its versatility and robustness in handling a broad range of constraints to generate more realistic trajectories compared to existing methods.