ARL2: Aligning Retrievers for Black-box Large Language Models via Self-guided Adaptive Relevance Labeling
CoRR(2024)
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
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 .
更多查看译文
AI 理解论文
溯源树
样例
生成溯源树,研究论文发展脉络
Chat Paper
正在生成论文摘要