Researchers have developed LEBGen, a novel framework that enhances Bayesian networks with large language models (LLMs) to improve the generation of travel survey data from limited samples. This approach leverages LLM-generated behavioral knowledge to refine the Bayesian network structure, addressing limitations in capturing complex dependencies found in sparse datasets. In experiments using a 2% few-shot sample from the Hong Kong Travel Characteristics Survey, LEBGen significantly reduced distributional and dependency errors compared to existing methods. AI
IMPACT This framework could enable more efficient and accurate travel behavior analysis by improving synthetic data generation from limited survey samples.
RANK_REASON The cluster describes a new research paper detailing a novel framework for data generation. [lever_c_demoted from research: ic=1 ai=1.0]
- arXiv
- Bayesian network
- Hong Kong Travel Characteristics Survey
- Hugging Face
- Large language models
- LEBGen
AI-generated summary · Google Gemini · from 1 sources. How we write summaries →
