@inproceedings{zeng-etal-2025-kbalign,
    title = "{KBA}lign: Efficient Self Adaptation on Specific Textual Knowledge Bases",
    author = "Zeng, Zheni  and
      Chen, Yuxuan  and
      Yu, Shi  and
      Wang, Ruobing  and
      Yan, Yukun  and
      Liu, Zhenghao  and
      Wang, Shuo  and
      Han, Xu  and
      Liu, Zhiyuan  and
      Sun, Maosong",
    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.728/",
    doi = "10.18653/v1/2025.findings-emnlp.728",
    pages = "13519--13532",
    ISBN = "979-8-89176-335-7",
    abstract = "Although retrieval-augmented generation (RAG) remains essential for knowledge-based question answering (KBQA), current paradigms face critical challenges under specific domains. Existing methods struggle with targeted adaptation on small-scale KBs: vanilla unsupervised training exhibits poor effectiveness, while fine-tuning incurs prohibitive costs of external signals. We present KBAlign, a self-supervised framework that enhances RAG systems through efficient model adaptation. Our key insight is to leverage the model{'}s intrinsic capabilities for knowledge alignment through two innovative mechanisms: multi-grained self-annotation that captures global knowledge for data construction, and iterative tuning that accelerates convergence through self verification. This framework enables cost-effective model adaptation to specific textual KBs, without human supervision or external model assistance. Experiments demonstrate that KBAlign can achieve 90{\%} of the performance gain obtained through GPT-4-supervised adaptation, while relying entirely on self-annotation of much smaller models. KBAlign significantly improves downstream QA accuracy across multiple domains with tiny costs, particularly benefiting scenarios requiring deep knowledge integration from specialized corpora. We release our experimental data, models, and process analyses to the community for further exploration(https://anonymous.4open.science/r/KBAlign-D160)."
}