@inproceedings{zheng-etal-2025-long-form,
    title = "Long-Form Information Alignment Evaluation Beyond Atomic Facts",
    author = "Zheng, Danna  and
      Lapata, Mirella  and
      Pan, Jeff Z.",
    editor = "Christodoulopoulos, Christos  and
      Chakraborty, Tanmoy  and
      Rose, Carolyn  and
      Peng, Violet",
    booktitle = "Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing",
    month = nov,
    year = "2025",
    address = "Suzhou, China",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/ingest-emnlp/2025.emnlp-main.558/",
    pages = "11018--11038",
    ISBN = "979-8-89176-332-6",
    abstract = "Information alignment evaluators are vital for various NLG evaluation tasks and trustworthy LLM deployment, reducing hallucinations and enhancing user trust. Current fine-grained methods, like FactScore, verify facts individually but neglect inter-fact dependencies, enabling subtle vulnerabilities.In this work, we introduce MontageLie, a challenging benchmark that constructs deceptive narratives by ``montaging'' truthful statements without introducing explicit hallucinations.We demonstrate that both coarse-grained LLM-based evaluators and current fine-grained frameworks are susceptible to this attack, with AUC-ROC scores falling below 65{\%}.To enable more robust fine-grained evaluation, we propose DoveScore, a novel framework that jointly verifies factual accuracy and event-order consistency. By modeling inter-fact relationships, DoveScore outperforms existing fine-grained methods by over 8{\%}, providing a more robust solution for long-form text alignment evaluation. Our code and datasets are available at https://github.com/dannalily/DoveScore."
}