@inproceedings{cheng-etal-2026-graphsynth,
    title = "{G}raph{S}ynth: Resolving the Diversity-Reliability Trade-off with Probabilistic Factor Graphs",
    author = "Cheng, Zehua  and
      Dai, Wei  and
      Sun, Jiahao  and
      Lukasiewicz, Thomas",
    editor = "Liakata, Maria  and
      Moreira, Viviane P.  and
      Zhang, Jiajun  and
      Jurgens, David",
    booktitle = "Proceedings of the 64th Annual Meeting of the {A}ssociation for {C}omputational {L}inguistics (Volume 1: Long Papers)",
    month = jul,
    year = "2026",
    address = "San Diego, California, United States",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/ingest-acl/2026.acl-long.1969/",
    pages = "42527--42543",
    ISBN = "979-8-89176-390-6",
    abstract = "The large language models offer a scaleable solution for the generation of synthetic data faced with a trade-off between maintaining the diversity of generation and achieving factually accurate results. This paper introduces Graphsynth, a framework which leverages a probabilistic factor graph modeling the universe of attributes. The framework leverages a high-level schema mapping compiled into efficient hard masks during the decoding phase for maintaining the syntactic truth and a span-synchronized verifier for dismissing logical contradictions at the decode time. The experiments conducted on biomedical, legal, and generic domains show that the method outperforms the state-of-the-art baselines with a structural integrity approaching perfection, a coverage of around 94{\%} attributes on the factor graph solution, and a boost in performance on downstream tasks such as +17.9{\%} on TruthfulQA."
}