ARL2：通过自引导自适应相关性标注为黑盒大型语言模型对齐检索器
ARL2: Aligning Retrievers for Black-box Large Language Models via Self-guided Adaptive Relevance Labeling
AI总结：
提出ARL2检索器学习技术，利用黑盒LLM作为标注器对证据打分，并结合自适应自训练策略降低标注成本，显著提升了检索准确率与零样本泛化能力。
摘要：
检索增强生成通过整合来自外部知识源的相关信息来增强大型语言模型（LLMs）。这使得LLMs能够适应特定领域，并减轻在知识密集型任务中的幻觉问题。然而，由于独立的训练过程和LLMs的黑盒特性，现有的检索器常常与LLMs不对齐。为了应对这一挑战，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利用LLMs对相关证据进行标注和打分，从而实现从稳健的LLM监督中学习检索器。此外，ARL2采用自适应自训练策略来整理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，与最先进的方法相比，在NQ上实现了5.4%的准确率提升，在MMLU上实现了4.6%的提升。此外，ARL2展现出稳健的迁移学习能力和强大的零样本泛化能力。我们的代码将发布于https://github.com/zhanglingxi-cs/ARL2。
英文摘要：
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}.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
