Mitigating Catastrophic Forgetting in Large Language Models with Self-Synthesized Rehearsal

arXiv:2403.01244v1 Announce Type: new
Abstract: Large language models (LLMs) suffer from catastrophic forgetting during continual learning. Conventional rehearsal-based methods rely on previous training data to retain the model's ability, which may not be feasible in real-world applications. When conducting continual learning based on a publicly-released LLM checkpoint, the availability of the original training data may be non-existent. To address this challenge, we propose a framework called Self-Synthesized Rehearsal (SSR) that uses the LLM to generate synthetic instances for rehearsal. Concretely, …

abstract applications arxiv availability catastrophic forgetting continual cs.ai cs.cl data language language models large language large language models llm llms synthesized training training data type world