Aligning LLM with Humans for Travel Choices: A Persona-Based Embedding Learning Approach
提出一种新框架，通过从数据中推断出行者角色并学习嵌入函数，使大语言模型在稀疏数据下也能准确预测出行选择，在瑞士地铁数据集上优于现有方法。
Large Language Models (LLMs) offer significant potential by serving as human proxies to advance travel demand modeling, but their behavioral misalignment with human travelers remains a critical obstacle. Furthermore, existing alignment methods are often impractical or inefficient when applied to the sparse data sets typically available for travel choices, limiting the adoption of these powerful new tools. We introduce a novel framework to align LLMs with travel choice behavior. Our method first infers a set of traveler personas from empirical data and then estimates a persona loading function that uses learned embeddings to select the appropriate persona for an individual based on their sociodemographics. Validated on the Swissmetro mode choice data set, our approach significantly outperforms established benchmarks in predicting both aggregate and individual choice outcomes. Our research offers a more adaptable, interpretable, and resource-efficient pathway to robust LLM-based travel behavior simulation, paving the way to integrate LLMs into transportation modeling practice in the future. Funding: This work was supported by the National Science Foundation Division of Civil, Mechanical and Manufacturing Innovation [Grants 2233057, 2240981]. Supplemental Material: The online appendix is available at https://doi.org/10.1287/trsc.2025.0330 .