Chain-of-Planned-Behaviour Workflow Elicits Few-Shot Mobility Generation in LLMs

TL;DR

This paper introduces the Chain-of-Planned Behaviour workflow for LLMs, inspired by the Theory of Planned Behaviour, to improve human mobility intention generation and reduce costs through integration with mechanistic models.

Contribution

It develops a novel LLM workflow based on TPB factors, significantly enhances mobility intention accuracy, and combines it with mechanistic models to reduce token costs and improve scalability.

Findings

Error rate reduced from 57.8% to 19.4%.

Token cost decreased by 97.7%.

Fine-tuning LLaMA with generated labels improves performance.

Abstract

The powerful reasoning capabilities of large language models (LLMs) have brought revolutionary changes to many fields, but their performance in human behaviour generation has not yet been extensively explored. This gap likely emerges because the internal processes governing behavioral intentions cannot be solely explained by abstract reasoning. Instead, they are also influenced by a multitude of factors, including social norms and personal preference. Inspired by the Theory of Planned Behaviour (TPB), we develop a LLM workflow named Chain-of-Planned Behaviour (CoPB) for mobility behaviour generation, which reflects the important spatio-temporal dynamics of human activities. Through exploiting the cognitive structures of attitude, subjective norms, and perceived behaviour control in TPB, CoPB significantly enhance the ability of LLMs to reason the intention of next movement. Specifically, CoPB substantially reduces the error rate of mobility intention generation from 57.8% to 19.4%. To improve the scalability of the proposed CoPB workflow, we further explore the synergy between LLMs and mechanistic models. We find mechanistic mobility models, such as gravity model, can effectively map mobility intentions to physical mobility behaviours. The strategy of integrating CoPB with gravity model can reduce the token cost by 97.7% and achieve better performance simultaneously. Besides, the proposed CoPB workflow can facilitate GPT-4-turbo to automatically generate high quality labels for mobility behavior reasoning. We show such labels can be leveraged to fine-tune the smaller-scale, open source LLaMA 3-8B, which significantly reduces usage costs without sacrificing the quality of the generated behaviours.