Year: 2026
Type: conference-paper
Abstract: GPS trajectories encode rich behavioral information about how people move, organize activities, and form daily routines.Recent advances in large language models (LLMs) raise a natural question: can such models infer and summarize travel behavior directly from mobility traces?This paper introduces Travel-BehaviorQA, a large-scale benchmark dataset that reframes trajectory analysis as a languagebased behavioral understanding task.The dataset links raw GPS trajectories with humangrounded question-answering (QA) pairs that capture travel intensity, temporal structure, activity patterns, mode usage, and behavioral routines.Unlike prior mobility datasets focused on prediction or classification, TravelBehaviorQA emphasizes semantic interpretation through a unified mix of deterministic and open-ended questions.In this benchmark, we construct over 143k QA instances spanning users and years, and evaluate a broad range of state-of-the-art LLMs under controlled settings.Our results reveal substantial gaps between factual extraction and genuine behavioral reasoning, showing that model scale alone is insufficient and that trajectory representation is a primary bottleneck.TravelBehaviorQA exposes critical limitations of current models and establishes a rigorous benchmark for advancing language-based understanding of human mobility behavior.
Authors: Dongyang Zhen, Niping Duan, Huan Zhou, Qingbin Cui
Institution: University of Maryland, College Park
Language: English
Subfield: Transportation
Field: Social Sciences
Domain: Social Sciences
Open Access status: hybrid
Funder: Federal Transit Administration
Award: G7260278488
OpenAlex ID: W7166825203