Generating Individual Travel Diaries Using Large Language Models Informed by Census and Land-Use Data
Aggregate validation confirms the LLM's statistical representativeness and establishes a quantifiable metric of diary realism for future synthetic diary evaluation systems, demonstrating LLM's zero-shot viability and establishing a quantifiable metric of diary realism for future synthetic diary evaluation systems.
Sepehr Golrokh Amin, Devin Rhoads, F. Fakhrmoosavi et al.
· arXiv.org · 1 citation