@inproceedings{bu-etal-2025-kaede,
    title = "{K}ae{D}e: Progressive Generation of Logical Forms via Knowledge-Aware Question Decomposition for Improved {KBQA}",
    author = "Bu, Ranran  and
      Cao, Jian  and
      Gao, Jianqi  and
      Qian, Shiyou  and
      Cai, Hongming",
    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.582/",
    doi = "10.18653/v1/2025.findings-emnlp.582",
    pages = "10958--10973",
    ISBN = "979-8-89176-335-7",
    abstract = "Knowledge base question answering (KBQA) refers to the task of answering natural language questions using large-scale structured knowledge bases (KBs). Existing semantic parsing-based (SP-based) methods achieve superior performance by directly converting questions into structured logical form (LF) queries using fine-tuned large language models (LLMs). However, these methods face the key challenge of difficulty in directly generating LFs for complex graph structures, which often leads to non-executable LFs that negatively impact overall KBQA performance. To address this challenge, we propose KaeDe, a novel generate-then-retrieve method for KBQA. This approach integrates knowledge-aware question decomposition and subsequent progressive LF generation within the generation phase, followed by an unsupervised retrieval phase. Specifically, the original question is decomposed into simplified, topic entity-centric sub-questions and explanations within the KB context. Path-level LFs are derived from these intermediate expressions and then combined into a comprehensive graph-level LF. Finally, the LF is refined through unsupervised entity and relation retrieval. Experimental results demonstrate that our method achieves state-of-the-art (SOTA) performance on WebQuestionSP (WebQSP) and ComplexWebQuestions (CWQ) benchmarks, particularly with fewer model parameters."
}