Paper Overview
Research field: NLP Authors: Narges Ahmadi, Yubo Jiao, Jonatas Augusto Manzolli, Jiangbo Yu Published: 2026-08-22 arXiv: 2608.20320
Summary
Travel behavior research increasingly combines digital data collection and predictive modeling, but these stages are typically developed and evaluated separately. This paper proposes a three-agent workflow that integrates conversational data collection, structured data processing, and behavioral prediction.
A chatbot-managed, image-enhanced stated preference survey collected mode choices from student commuters under five predefined weather scenarios, producing 454 subject-scenario observations. Weather associations were analyzed using a multinomial Logit model, while logistic regression and random forests provided machine learning baselines.
The authors evaluated nine locally deployed LLMs (2B to 35B parameters) covering four zero-shot prompting conditions as well as extended persona, few-shot, and visual configurations.
Key Findings
- Random forest achieved 69.6% five-class accuracy
- The best text-only zero-shot LLM reached 69.9% accuracy without task-specific fitting
- Habitual travel information produced the most consistent gains
- Expert framing generally outperformed role-playing prompts
- Visual configurations achieved the best result at 71.5% accuracy
*Auto-collected on 2026-08-22*