@inproceedings{zhang-etal-2025-divide,
    title = "Divide-Verify-Refine: Can {LLM}s Self-align with Complex Instructions?",
    author = "Zhang, Xianren  and
      Tang, Xianfeng  and
      Liu, Hui  and
      Wu, Zongyu  and
      He, Qi  and
      Lee, Dongwon  and
      Wang, Suhang",
    editor = "Che, Wanxiang  and
      Nabende, Joyce  and
      Shutova, Ekaterina  and
      Pilehvar, Mohammad Taher",
    booktitle = "Findings of the Association for Computational Linguistics: ACL 2025",
    month = jul,
    year = "2025",
    address = "Vienna, Austria",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/landing_page/2025.findings-acl.709/",
    pages = "13783--13800",
    ISBN = "979-8-89176-256-5",
    abstract = "Recent studies show LLMs struggle with complex instructions involving multiple constraints (e.g., length, format, sentiment). Existing research enhances open-source LLMs using closed-source guidance (e.g., GPT-4), but this heavily relies on generated data quality. An alternative is leveraging LLMs' self-correction to refine responses for better constraint adherence. However, this is limited by the feedback quality, as we found LLMs cannot generate reliable feedback or detect errors. Moreover, the self-correction effectiveness relies on few-shot examples illustrating response modifications. As constraints in complex instructions are diverse, manually crafting such examples for each constraint type can be labor-intensive and sub-optimal. To address these two challenges, we propose the Divide-Verify-Refine (DVR) framework with three steps: (1) Divide complex instructions into single constraints and prepare appropriate tools; (2) Verify responses using tools that provide rigorous check and textual guidance (e.g., Python scripts for format checks or pre-trained classifiers for content analysis); (3) Refine: To maximize refinement effectiveness, we propose dynamic few-shot prompting, where a refinement repository collects successful refinements, and these examples are selectively retrieved for future refinements. Recognizing the lack of complexity in existing datasets, we create a new dataset of complex instructions. DVR doubles Llama3.1-8B{'}s constraint adherence and triples Mistral-7B{'}s performance."
}