@inproceedings{38c951f6804e41069cc693195a1ba1ee,
title = "SEAKR: Self-aware Knowledge Retrieval for Adaptive Retrieval Augmented Generation",
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 retrieval 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 retrieval methods.",
author = "Zijun Yao and Weijian Qi and Liangming Pan and Shulin Cao and Linmei Hu and Weichuan Liu and Lei Hou and Juanzi Li",
note = "Publisher Copyright: {\textcopyright} 2025 Association for Computational Linguistics.; 63rd Annual Meeting of the Association for Computational Linguistics, ACL 2025 ; Conference date: 27-07-2025 Through 01-08-2025",
year = "2025",
doi = "10.18653/v1/2025.acl-long.1312",
language = "English",
series = "Proceedings of the Annual Meeting of the Association for Computational Linguistics",
publisher = "Association for Computational Linguistics (ACL)",
pages = "27022--27043",
editor = "Wanxiang Che and Joyce Nabende and Ekaterina Shutova and Pilehvar, \{Mohammad Taher\}",
booktitle = "Long Papers",
address = "United States",
}