@inproceedings{liu-etal-2025-e,
    title = "{E}-Verify: A Paradigm Shift to Scalable Embedding-based Factuality Verification",
    author = "Liu, Zeyang  and
      Xue, Jingfeng  and
      Yang, Xiuqi  and
      Du, Wenbiao  and
      Fu, Jiarun  and
      Chen, Junbao  and
      Guo, Wenjie  and
      Wang, Yong",
    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.308/",
    doi = "10.18653/v1/2025.findings-emnlp.308",
    pages = "5759--5776",
    ISBN = "979-8-89176-335-7",
    abstract = "Large language models (LLMs) exhibit remarkable text-generation capabilities, yet struggle with factual consistency, motivating growing interest in factuality verification. Existing factuality verification methods typically follow a \textit{Decompose-Then-Verify} paradigm, which improves granularity but suffers from poor scalability and efficiency. We propose a novel \textbf{ \textit{Decompose-Embed-Interact}} paradigm that shifts factuality verification from costly text-level reasoning to efficient alignment in embedding space, effectively mitigating the scalability bottlenecks and computational inefficiencies inherent to prior approaches. While the proposed paradigm promises scalable verification, its implementation faces three practical challenges: efficient decomposition, factually faithful embedding, and accurate verification in embedding space. To address these challenges, we introduce \textbf{E-Verify}, a lightweight framework that resolves them through three specially designed modules, each aligned with a specific stage of the paradigm and designed to preserve scalability and efficiency. Experiments demonstrate that E-Verify significantly improves both decomposition and verification efficiency while maintaining competitive accuracy. These results confirm that the proposed paradigm enables scalable and fine-grained factuality verification with minimal performance trade-offs."
}