元认知检索增强大型语言模型
Metacognitive Retrieval-Augmented Large Language Models
AI总结：
本文提出MetaRAG方法，将检索增强生成与元认知相结合，通过三步元认知调节流程使模型自我反思并修复认知不足，显著提升了多跳推理任务的响应准确性。
摘要：
检索增强生成因其生成事实性内容的有效性，已成为自然语言处理的核心。传统方法采用单次检索，而近期方法转向多次检索以处理多跳推理任务。然而，这些策略受限于预定义的推理步骤，可能导致响应生成不准确。本文提出MetaRAG，将检索增强生成过程与元认知相结合。借鉴认知心理学，元认知使实体能够自我反思并批判性评估其认知过程。通过整合这一点，MetaRAG使模型能够监控、评估和规划其响应策略，增强其内省推理能力。通过三步元认知调节流程，模型可识别初始认知响应中的不足并加以修复。实证评估表明，MetaRAG显著优于现有方法。
英文摘要：
Retrieval-augmented generation have become central in natural language processing due to their efficacy in generating factual content. While traditional methods employ single-time retrieval, more recent approaches have shifted towards multi-time retrieval for multi-hop reasoning tasks. However, these strategies are bound by predefined reasoning steps, potentially leading to inaccuracies in response generation. This paper introduces MetaRAG, an approach that combines the retrieval-augmented generation process with metacognition. Drawing from cognitive psychology, metacognition allows an entity to self-reflect and critically evaluate its cognitive processes. By integrating this, MetaRAG enables the model to monitor, evaluate, and plan its response strategies, enhancing its introspective reasoning abilities. Through a three-step metacognitive regulation pipeline, the model can identify inadequacies in initial cognitive responses and fixes them. Empirical evaluations show that MetaRAG significantly outperforms existing methods.
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。
