RAG-R1：通过多查询并行性激励大语言模型的搜索与推理能力
RAG-R1: Incentivizing the Search and Reasoning Capabilities of LLMs through Multi-query Parallelism
AI总结：
RAG-R1通过多查询并行性提升大语言模型的搜索与推理能力，实验显示其在问答基准中性能优于基线方法，推理效率提升显著。
摘要：
大型语言模型（LLMs）尽管具有显著的能力，但由于其内部知识静态，容易生成幻觉或过时的内容。虽然将检索增强生成（RAG）与强化学习（RL）相结合提供了解决方案，但这些方法本质上受到单一查询模式的限制，导致延迟过高且固有脆弱。为克服这些限制，我们引入了RAG-R1，一种新的两阶段训练框架，核心是多查询并行性。我们的框架使LLMs在推理过程中能够自适应地利用内部和外部知识，从单一查询模式过渡到多查询并行性。这种架构转变增强了推理的鲁棒性，同时显著减少了推理延迟。在七个问答基准测试中进行了广泛的实验，证实了我们方法的优越性，该方法在最强基线之上表现优异，最高提升达13.7%，推理时间减少11.1%。
英文摘要：
Large Language Models (LLMs), despite their remarkable capabilities, are prone to generating hallucinated or outdated content due to their static internal knowledge. While Retrieval-Augmented Generation (RAG) integrated with Reinforcement Learning (RL) offers a solution, these methods are fundamentally constrained by a single-query mode, leading to prohibitive latency and inherent brittleness. To overcome these limitations, we introduce RAG-R1, a novel two-stage training framework centered around multi-query parallelism. Our framework enables LLMs to adaptively leverage internal and external knowledge during the reasoning process while transitioning from the single-query mode to multi-query parallelism. This architectural shift bolsters reasoning robustness while significantly reducing inference latency. Extensive experiments on seven question-answering benchmarks confirm the superiority of our method, which outperforms the strongest baseline by up to 13.7% and decreases inference time by 11.1%.
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。
