@inproceedings{tian-etal-2025-compkbqa,
    title = "{C}omp{KBQA}: Component-wise Task Decomposition for Knowledge Base Question Answering",
    author = "Tian, Yuhang  and
      Song, Dandan  and
      Wu, Zhijing  and
      Yang, Pan  and
      Zhou, Changzhi  and
      Yang, Jun  and
      Wang, Hao  and
      Ma, Huipeng  and
      Li, Chenhao  and
      Zhang, Luan",
    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.16/",
    pages = "293--309",
    ISBN = "979-8-89176-332-6",
    abstract = "Knowledge Base Question Answering (KBQA) aims to extract accurate answers from the Knowledge Base (KB). Traditional Semantic Parsing (SP)-based methods are widely used but struggle with complex queries. Recently, large language models (LLMs) have shown promise in improving KBQA performance. However, the challenge of generating error-free logical forms remains, as skeleton, topic Entity, and relation Errors still frequently occur. To address these challenges, we propose CompKBQA(Component-wise Task Decomposition for Knowledge Base Question Answering), a novel framework that optimizes the process of fine-tuning a LLM for generating logical forms by enabling the LLM to progressively learn relevant sub-tasks like skeleton generation, topic entity generation, and relevant relations generation. Additionally, we propose $R^3$, which retrieves and incorporates KB information into the process of logical form generation. Experimental evaluations on two benchmark KBQA datasets, WebQSP and CWQ, demonstrate that CompKBQA achieves state-of-the-art performance, highlighting the importance of task decomposition and KB-aware learning."
}