@inproceedings{gottal-matthes-2026-verifiable,
    title = "Verifiable Parameterization of {B}ayesian Networks from Scientific Literature: Unlocking Unstructured Empirical Evidence",
    author = "Gottal, Jonas  and
      Matthes, Florian",
    editor = "Liakata, Maria  and
      Moreira, Viviane P.  and
      Zhang, Jiajun  and
      Jurgens, David",
    booktitle = "Findings of the {A}ssociation for {C}omputational {L}inguistics: {ACL} 2026",
    month = jul,
    year = "2026",
    address = "San Diego, California, United States",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/ingest-acl/2026.findings-acl.167/",
    pages = "3400--3414",
    ISBN = "979-8-89176-395-1",
    abstract = "Learning Bayesian Networks typically requires access to raw tabular data to estimate conditional probabilities. However, in many scientific domains, raw data is unavailable due to privacy concerns or general lack of access, while structured statistical summaries are increasingly accessible through large language models and published literature. We propose and evaluate five distinct strategies to reconstruct local conditional probability tables solely from statistical summaries in order to parameterize Bayesian Networks. Our comprehensive evaluation across mixed-type synthetic networks demonstrates that copula-based methods significantly outperform standard baselines, offering a viable path for knowledge integration from heterogeneous sources {--} unlocking the wealth of published knowledge for causal modeling while ensuring transparency and verifiability."
}