Metacognitive Retrieval-Augmented Large Language Models
This addresses the issue of predefined reasoning steps in NLP tasks, offering a novel approach for enhancing factual content generation, though it appears incremental in building on retrieval-augmented methods.
The paper tackles the problem of inaccuracies in retrieval-augmented generation for multi-hop reasoning by introducing MetaRAG, which integrates metacognition to enable self-reflection and strategy planning, resulting in significant performance improvements over existing methods.
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.