{"ID":2847279,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2511.00574","arxiv_id":"2511.00574","title":"Bayesian Network Structure Discovery Using Large Language Models","abstract":"Understanding probabilistic dependencies among variables is central to analyzing complex systems. Traditional structure learning methods often require extensive observational data or are limited by manual, error-prone incorporation of expert knowledge. Recent studies have explored using large language models (LLMs) for structure learning, but most treat LLMs as auxiliary tools for pre-processing or post-processing, leaving the core learning process data-driven. In this work, we introduce a unified framework for Bayesian network structure discovery that places LLMs at the center, supporting both data-free and data-aware settings. In the data-free regime, we introduce \\textbf{PromptBN}, which leverages LLM reasoning over variable metadata to generate a complete directed acyclic graph (DAG) in a single call. PromptBN effectively enforces global consistency and acyclicity through dual validation, achieving constant $\\mathcal{O}(1)$ query complexity. When observational data are available, we introduce \\textbf{ReActBN} to further refine the initial graph. ReActBN combines statistical evidence with LLM by integrating a novel ReAct-style reasoning with configurable structure scores (e.g., Bayesian Information Criterion). Experiments demonstrate that our method outperforms prior data-only, LLM-only, and hybrid baselines, particularly in low- or no-data regimes and on out-of-distribution datasets. Code is available at https://github.com/sherryzyh/llmbn.","short_abstract":"Understanding probabilistic dependencies among variables is central to analyzing complex systems. Traditional structure learning methods often require extensive observational data or are limited by manual, error-prone incorporation of expert knowledge. Recent studies have explored using large language models (LLMs) for...","url_abs":"https://arxiv.org/abs/2511.00574","url_pdf":"https://arxiv.org/pdf/2511.00574v2","authors":"[\"Yinghuan Zhang\",\"Yufei Zhang\",\"Parisa Kordjamshidi\",\"Zijun Cui\"]","published":"2025-11-01T14:32:52Z","proceeding":"cs.LG","tasks":"[\"cs.LG\"]","methods":"[\"Large Language Model\",\"Language Model\"]","has_code":false,"code_links":[{"ID":607509,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_id":2847279,"paper_url":"https://arxiv.org/abs/2511.00574","paper_title":"Bayesian Network Structure Discovery Using Large Language Models","repo_url":"https://github.com/sherryzyh/llmbn","is_official":false,"mentioned_in_paper":false,"mentioned_in_github":true,"github_stars":0}]}