@inproceedings{yao-etal-2025-seakr,
    title = "{S}ea{KR}: Self-aware Knowledge Retrieval for Adaptive Retrieval Augmented Generation",
    author = "Yao, Zijun  and
      Qi, Weijian  and
      Pan, Liangming  and
      Cao, Shulin  and
      Hu, Linmei  and
      Weichuan, Liu  and
      Hou, Lei  and
      Li, Juanzi",
    editor = "Che, Wanxiang  and
      Nabende, Joyce  and
      Shutova, Ekaterina  and
      Pilehvar, Mohammad Taher",
    booktitle = "Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)",
    month = jul,
    year = "2025",
    address = "Vienna, Austria",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/ingestion-acl-25/2025.acl-long.1312/",
    pages = "27022--27043",
    ISBN = "979-8-89176-251-0",
    abstract = "Adaptive Retrieval-Augmented Generation (RAG) is an effective strategy to alleviate hallucination of large language models (LLMs). It dynamically determines whether LLMs need external knowledge for generation and invokes retrieval accordingly. This paper introduces Self-aware Knowledge Retrieval (SeaKR), a novel adaptive RAG model that extracts self-aware uncertainty of LLMs from their internal states. SeaKR activates retrieval when the LLMs present high self-aware uncertainty for generation. To effectively integrate retrieved knowledge snippets, SeaKR re-ranks them based on LLM{'}s self-aware uncertainty to preserve the snippet that reduces their uncertainty to the utmost. To facilitate solving complex tasks that require multiple retrievals, SeaKR utilizes their self-aware uncertainty to choose among different reasoning strategies. Our experiments on both complex and simple Question Answering datasets show that SeaKR outperforms existing adaptive RAG methods."
}