Paper ID: 2404.08707
Large Language Model Can Continue Evolving From Mistakes
Haokun Zhao, Haixia Han, Jie Shi, Chengyu Du, Jiaqing Liang, Yanghua Xiao
As world knowledge evolves and new task schemas emerge, Continual Learning (CL) is crucial for keeping Large Language Models (LLMs) up-to-date and addressing their shortcomings. LLMs typically require continual instruction tuning (CIT) and continual pre-training (CPT) to adapt to new tasks and acquire essential knowledge. However, collecting sufficient CPT data while addressing knowledge gaps remains challenging, as does optimizing the efficiency of utilizing this data. Inspired by the 'summarizing mistakes' strategy, we propose the Continue Evolving from Mistakes (CEM) method, a data-efficient approach aiming to collect CPT data and continually improve LLMs' performance through iterative evaluation and supplementation with mistake-relevant knowledge. To enhance data utilization and mitigate forgetting, we introduce a novel training paradigm that combines CIT and CPT data. Experiments demonstrate that CEM significantly enhances model performance and continual evolution. The code and dataset are available in the GitHub.
Submitted: Apr 11, 2024