An Empirical Study of Catastrophic Forgetting in Large Language Models During Continual Fine-tuning

arXiv:2308.08747v3 Announce Type: replace
Abstract: Catastrophic forgetting (CF) is a phenomenon that occurs in machine learning when a model forgets previously learned information while acquiring new knowledge. As large language models (LLMs) have demonstrated remarkable performance, it is intriguing to investigate whether CF exists during the continual instruction tuning of LLMs. This study empirically evaluates the forgetting phenomenon in LLMs' knowledge during continual instruction tuning from the perspectives of domain knowledge, reasoning, and reading comprehension. The experiments reveal that catastrophic …

abstract arxiv catastrophic forgetting continual cs.cl fine-tuning information knowledge language language models large language large language models llms machine machine learning performance study type