Know More, Know Clearer: A Meta-Cognitive Framework for Knowledge Augmentation in Large Language Models
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2026
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866908833597620224 |
|---|---|
| author | Chen, Hao He, Ye Fan, Yuchun Yan, Yukun Liu, Zhenghao Zhu, Qingfu Sun, Maosong Che, Wanxiang |
| author_facet | Chen, Hao He, Ye Fan, Yuchun Yan, Yukun Liu, Zhenghao Zhu, Qingfu Sun, Maosong Che, Wanxiang |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2602_12996 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | Know More, Know Clearer: A Meta-Cognitive Framework for Knowledge Augmentation in Large Language Models Chen, Hao He, Ye Fan, Yuchun Yan, Yukun Liu, Zhenghao Zhu, Qingfu Sun, Maosong Che, Wanxiang Computation and Language Artificial Intelligence 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. |
| title | Know More, Know Clearer: A Meta-Cognitive Framework for Knowledge Augmentation in Large Language Models |
| topic | Computation and Language Artificial Intelligence |
| url | https://arxiv.org/abs/2602.12996 |