@inproceedings{qiao-etal-2025-supportiveness,
    title = "Supportiveness-based Knowledge Rewriting for Retrieval-augmented Language Modeling",
    author = "Qiao, Zile  and
      Ye, Wei  and
      Jiang, Yong  and
      Mo, Tong  and
      Xie, Pengjun  and
      Li, Weiping  and
      Huang, Fei  and
      Zhang, Shikun",
    editor = "Chiruzzo, Luis  and
      Ritter, Alan  and
      Wang, Lu",
    booktitle = "Findings of the Association for Computational Linguistics: NAACL 2025",
    month = apr,
    year = "2025",
    address = "Albuquerque, New Mexico",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/landing_page/2025.findings-naacl.148/",
    pages = "2728--2740",
    ISBN = "979-8-89176-195-7",
    abstract = "Retrieval-augmented language models (RALMs) have recently shown great potential in mitigating the limitations of implicit knowledge in LLMs, such as untimely updating of the latest expertise and unreliable retention of long-tail knowledge. However, since the external knowledge base, as well as the retriever, can not guarantee reliability, potentially leading to the knowledge retrieved not being helpful or even misleading for LLM generation. In this paper, we introduce Supportiveness-based Knowledge Rewriting (SKR), a robust and pluggable knowledge rewriter inherently optimized for LLM generation. Specifically, we introduce the novel concept of {\textquotedblleft}supportiveness{\textquotedblright}{---}which represents how effectively a knowledge piece facilitates downstream tasks. Based on supportiveness, we first design a training data curation strategy for our rewriter model, effectively identifying and filtering out poor or irrelevant rewrites to improve data efficacy. We then introduce the direct preference optimization (DPO) algorithm to align the generated rewrites to optimal supportiveness, guiding the rewriter model to summarize augmented content that better improves the final response. Comprehensive evaluations across six popular knowledge-intensive tasks and four LLMs have demonstrated the effectiveness and superiority of SKR. With only 7B parameters, SKR has shown better knowledge rewriting capability over GPT-4."
}