@inproceedings{marinescu-etal-2025-factreasoner,
    title = "{F}act{R}easoner: A Probabilistic Approach to Long-Form Factuality Assessment for Large Language Models",
    author = "Marinescu, Radu  and
      Bhattacharjya, Debarun  and
      Lee, Junkyu  and
      Tchrakian, Tigran T.  and
      Carnerero-Cano, Javier  and
      Hou, Yufang  and
      Daly, Elizabeth M.  and
      Pascale, Alessandra",
    editor = "Christodoulopoulos, Christos  and
      Chakraborty, Tanmoy  and
      Rose, Carolyn  and
      Peng, Violet",
    booktitle = "Findings of the Association for Computational Linguistics: EMNLP 2025",
    month = nov,
    year = "2025",
    address = "Suzhou, China",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/author-page-yu-wang-polytechnic/2025.findings-emnlp.785/",
    doi = "10.18653/v1/2025.findings-emnlp.785",
    pages = "14547--14577",
    ISBN = "979-8-89176-335-7",
    abstract = "Large language models (LLMs) have achieved remarkable success in generative tasks, yet they often fall short in ensuring the factual accuracy of their outputs thus limiting their reliability in real-world applications where correctness is critical. In this paper, we present FactReasoner, a novel neuro-symbolic based factuality assessment framework that employs probabilistic reasoning to evaluate the truthfulness of long-form generated responses. FactReasoner decomposes a response into atomic units, retrieves relevant contextual information from external knowledge sources, and models the logical relationships (e.g., entailment, contradiction) between these units and their contexts using probabilistic encodings. It then estimates the posterior probability that each atomic unit is supported by the retrieved evidence. Our experiments on both labeled and unlabeled benchmark datasets demonstrate that FactReasoner often outperforms state-of-the-art prompt-based methods in terms of factual precision and recall."
}