InsCL: A Data-efficient Continual Learning Paradigm for Fine-tuning Large Language Models with Instructions
This work addresses the need for efficient continual learning in LLMs for real-life applications, offering an incremental improvement over existing replay-based methods.
The paper tackles the problem of catastrophic forgetting in large language models during continual learning by proposing InsCL, a method that uses instructions to guide replay strategies, achieving performance gains of 3.0 Relative Gain compared to Random Replay and 27.96 Relative Gain compared to No Replay.
Instruction tuning effectively optimizes Large Language Models (LLMs) for downstream tasks. Due to the changing environment in real-life applications, LLMs necessitate continual task-specific adaptation without catastrophic forgetting. Considering the heavy computational cost, replay-based Continual Learning (CL) methods are the simplest and most widely used for LLMs to address the forgetting issue. However, traditional replay-based methods do not fully utilize instructions to customize the replay strategy. In this work, we propose a novel paradigm called Instruction-based Continual Learning (InsCL). InsCL dynamically replays previous data based on task similarity, calculated by Wasserstein Distance with instructions. Moreover, we further introduce an Instruction Information Metric (InsInfo) to quantify the complexity and diversity of instructions. According to InsInfo, InsCL guides the replay process more inclined to high-quality data. We conduct extensive experiments over 16 tasks with different training orders, observing consistent performance improvements of InsCL. When all tasks have been trained, InsCL achieves performance gains of 3.0 Relative Gain compared with Random Replay, and 27.96 Relative Gain compared with No Replay.