SeaKR: Self-aware Knowledge Retrieval for Adaptive Retrieval Augmented
  Generation

Zijun Yao; Weijian Qi; Liangming Pan; Shulin Cao; Linmei Hu; Weichuan Liu; Lei Hou; Juanzi Li

返回文献探索

Paper · arXiv 2406.19215

SeaKR: Self-aware Knowledge Retrieval for Adaptive Retrieval Augmented Generation

Zijun Yao, Weijian Qi, Liangming Pan, Shulin Cao, Linmei Hu, Weichuan Liu, Lei Hou, Juanzi Li

32 upvotesJune 27, 2024arXiv 预印本

AI 摘要

SeaKR, an adaptive RAG model, improves knowledge retrieval by leveraging LLMs' self-aware uncertainty to activate, re-rank, and integrate knowledge appropriately, outperforming existing methods in QA tasks.

Self-aware Knowledge RetrievalSeaKRadaptive RAGself-aware uncertaintyLLMsinternal statesknowledge snippetsre-rankingreasoning strategiesQA datasets

Abstract

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. We release our code at https://github.com/THU-KEG/SeaKR.