Retrieval-augmented generation enhances large language models (LLMs) by incorporating relevant information from external knowledge sources. This enables LLMs to adapt to specific domains and mitigate hallucinations in knowledge-intensive tasks. However, existing retrievers are often misaligned with LLMs due to their separate training processes and the black-box nature of LLMs. To address this challenge, we propose ARL2, a retriever learning technique that harnesses LLMs as labelers. ARL2 leverages LLMs to annotate and score relevant evidence, enabling learning the retriever from robust LLM supervision. Furthermore, ARL2 uses an adaptive self-training strategy for curating high-quality and diverse relevance data, which can effectively reduce the annotation cost. Extensive experiments demonstrate the effectiveness of ARL2, achieving accuracy improvements of 5.4% on NQ and 4.6% on MMLU compared to the state-of-the-art methods. Additionally, ARL2 exhibits robust transfer learning capabilities and strong zero-shot generalization abilities. Our code will be published at \url{https://github.com/zhanglingxi-cs/ARL2}.

翻译：检索增强生成通过整合外部知识源中的相关信息来增强大语言模型（LLMs）的能力。这使得LLMs能够适应特定领域，并减轻知识密集型任务中的幻觉问题。然而，由于训练过程的分离以及LLMs的黑盒特性，现有的检索器往往与LLMs存在错位。为解决这一挑战，我们提出了ARL2，一种利用LLMs作为标注器的检索器学习技术。ARL2借助LLMs对相关证据进行标注和评分，从而能够在强大的LLM监督下学习检索器。此外，ARL2采用自适应自训练策略来筛选高质量且多样化的相关性数据，这能有效降低标注成本。大量实验证明了ARL2的有效性，与现有最先进方法相比，在NQ和MMLU数据集上分别实现了5.4%和4.6%的准确率提升。同时，ARL2展现出强大的迁移学习能力和优秀的零样本泛化能力。我们的代码将发布于 \url{https://github.com/zhanglingxi-cs/ARL2}。