Meta-Cognitive Framework for Knowledge Augmentation

Know More, Know Clearer: A Meta-Cognitive Framework for Knowledge Augmentation in Large Language Models

Announce Type: replace Abstract: 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.