ARL2: Aligning Retrievers with Black-box Large Language Models via Self-guided Adaptive Relevance Labeling

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 relevance evidence, enabling learning the retriever from robust LLM supervision. Furthermore, ARL2 uses a 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-ofthe-art methods. Additionally, ARL2 exhibits robust transfer learning capabilities and strong zero-shot generalization abilities.