知道更多，更清晰：大型语言模型中知识增强的元认知框架
Know More, Know Clearer: A Meta-Cognitive Framework for Knowledge Augmentation in Large Language Models
AI总结：
提出元认知框架，利用内部认知信号划分知识空间为掌握、混淆和缺失区域，通过差异化干预和认知一致性机制增强知识并校准置信度，实验证明优于基线方法。
摘要：
知识增强显著提升了大型语言模型（LLMs）在知识密集型任务中的性能。然而，现有方法通常基于模型性能等同于内部知识的简单前提，忽略了导致过度自信错误或不确定真相的知识-置信度差距。为弥合这一差距，我们提出了一种新颖的元认知框架，通过差异化干预和对齐实现可靠的知识增强。我们的方法利用内部认知信号将知识空间划分为掌握、混淆和缺失区域，指导有针对性的知识扩展。此外，我们引入了一种认知一致性机制，以同步主观确定性与客观准确性，确保校准的知识边界。大量实验表明，我们的框架持续优于强基线，验证了其在不仅增强知识能力，而且培养更好区分已知与未知的认知行为方面的合理性。所有代码均可在该 https URL 获取。
英文摘要：
Knowledge augmentation has significantly enhanced the performance of Large Language Models (LLMs) in knowledge-intensive tasks. However, existing methods typically operate on the simplistic premise that model performance equates with internal knowledge, overlooking the knowledge-confidence gaps that lead to overconfident errors or uncertain truths. To bridge this gap, we propose a novel meta-cognitive framework for reliable knowledge augmentation via differentiated intervention and alignment. Our approach leverages internal cognitive signals to partition the knowledge space into mastered, confused, and missing regions, guiding targeted knowledge expansion. Furthermore, we introduce a cognitive consistency mechanism to synchronize subjective certainty with objective accuracy, ensuring calibrated knowledge boundaries. Extensive experiments demonstrate the our framework consistently outperforms strong baselines, validating its rationality in not only enhancing knowledge capabilities but also fostering cognitive behaviors that better distinguish knowns from unknowns. All codes are available at https://github.com/AI9Stars/Know-More-Know-Clearer.
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。
