Researchers have developed a method for fine-tuning Large Language Models (LLMs) to predict tourist behavior, addressing the limitations of traditional models that struggle with context-dependent decisions. By leveraging the commonsense reasoning capabilities of LLMs and adapting them to specific locations, the approach can effectively model destination-specific patterns. Experiments using data from Wakayama Castle Park, Japan, demonstrated that a fine-tuned Llama-3.1-8B model achieved significant accuracy in predicting next points of interest and maintained performance even in undersampled scenarios like rainy days. AI
IMPACT This research demonstrates LLMs' potential for high-fidelity behavior modeling in specialized domains, enabling better planning for mobility interventions.
RANK_REASON The cluster contains an academic paper detailing a new research methodology for fine-tuning LLMs. [lever_c_demoted from research: ic=1 ai=1.0]
AI-generated summary · Google Gemini · from 1 sources. How we write summaries →
