让大模型自己判断是否需要查资料，提升问答效率
Probing-RAG: Self-Probing to Guide Language Models in Selective Document Retrieval
- 用模型中间层状态判断是否该检索
- 在5个数据集上表现更好且减少冗余检索
- 适合追求高效精准问答的开发者
检索增强生成（RAG）通过引入外部知识提升语言模型性能。然而，传统的一次性检索-生成流程在真实场景中不够灵活，有时需多次检索，有时则无需检索。本文提出Probing-RAG，利用语言模型中间层的隐藏状态表示，自适应判断当前查询是否需要额外检索。通过预训练的探测器，Probing-RAG能够有效捕捉模型内部认知状态，从而可靠决策是否调用外部文档。在五个开放域问答数据集上的实验表明，Probing-RAG优于以往方法，同时显著减少了冗余检索步骤。
原文摘要 · Abstract (English)
Retrieval-Augmented Generation (RAG) enhances language models by retrieving and incorporating relevant external knowledge. However, traditional retrieve-and-generate processes may not be optimized for real-world scenarios, where queries might require multiple retrieval steps or none at all. In this paper, we propose a Probing-RAG, which utilizes the hidden state representations from the intermediate layers of language models to adaptively determine the necessity of additional retrievals for a given query. By employing a pre-trained prober, Probing-RAG effectively captures the model's internal cognition, enabling reliable decision-making about retrieving external documents. Experimental results across five open-domain QA datasets demonstrate that Probing-RAG outperforms previous methods while reducing the number of redundant retrieval steps.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。