@inproceedings{liu-etal-2025-logic-long,
    title = "Logic: Long-form Outline Generation via Imitative and Critical Self-refinement",
    author = "Liu, Hengwei  and
      Shen, Yongliang  and
      Zheng, Zhe  and
      Ma, Haoyuan  and
      Wu, Xingyu  and
      Zhang, Yin  and
      Lu, Weiming",
    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.983/",
    doi = "10.18653/v1/2025.findings-emnlp.983",
    pages = "18119--18144",
    ISBN = "979-8-89176-335-7",
    abstract = "Long-form outline generation for expository articles requires both comprehensive knowledge coverage and logical coherence, which is essential for creating detailed Wikipedia-like content. However, existing methods face critical limitations: outlines generated in the pre-writing stage often have low knowledge density and lack detail, while retrieval-augmented approaches struggle to maintain logical coherence across retrieved information. Additionally, unlike human writers who can iteratively improve through peer feedback and reference similar topics, current approaches lack effective mechanisms for systematic outline refinement. To address these challenges, we propose Logic, a Long-form Outline Generation system via Imitative and Critical self-refinement that mimics human writers' refinement process. Logic establishes a coherent planning framework and structured knowledge base, learns from similar topic outlines through imitation, and continuously improves through model-based critique. Experiments on FreshWiki and our dataset WikiOutline show that, compared to the best baseline, Logic{'}s long-form outlines are more organized (with increases of 22.85{\%} and 21.65{\%} respectively) and more logically coherent (with increases of 16.19{\%} and 12.24{\%} respectively). Human evaluation further validates Logic{'}s effectiveness in generating comprehensive and well-structured long-form outlines."
}