@inproceedings{wang-etal-2025-self,
    title = "Self-{DC}: When to Reason and When to Act? Self Divide-and-Conquer for Compositional Unknown Questions",
    author = "Wang, Hongru  and
      Xue, Boyang  and
      Zhou, Baohang  and
      Zhang, Tianhua  and
      Wang, Cunxiang  and
      Wang, Huimin  and
      Chen, Guanhua  and
      Wong, Kam-Fai",
    editor = "Chiruzzo, Luis  and
      Ritter, Alan  and
      Wang, Lu",
    booktitle = "Proceedings of the 2025 Conference of the Nations of the Americas Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 1: Long Papers)",
    month = apr,
    year = "2025",
    address = "Albuquerque, New Mexico",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/fix-sig-urls/2025.naacl-long.331/",
    pages = "6510--6525",
    ISBN = "979-8-89176-189-6",
    abstract = "Previous research has typically concentrated on leveraging the internal knowledge of Large Language Models (LLMs) to answer known questions (i.e., internal reasoning such as generate-then-read). In contrast, for questions that fall outside their known scope, these models rely on external knowledge retrieval to provide accurate responses (i.e., external acting such as retrieve-then-read). However, few previous works consider the \textit{compositional questions}, which consist of several known and unknown sub-questions, necessitating the dynamic combination of previous two methods (i.e., \textit{internal reasoning and external acting}) to achieve a better trade-off between effectiveness and efficiency. To this end, we introduce a \textbf{Self} \textbf{D}ivide-and-\textbf{C}onquer (\textit{Self-DC}) framework, accompanying with the first \textbf{C}ompositional \textbf{u}nknown \textbf{Q}uestion-\textbf{A}nswering dataset (CuQA). This framework enables LLMs to adaptively choose between using internal knowledge and retrieving external knowledge as needed, resulting in a better trade-off between effectiveness and efficiency. Experimental results on two datasets demonstrate that \textit{Self-DC} can achieve comparable or even better performance with much fewer external calls compared with several strong baselines."
}