Progressive Prompts: Continual Learning for Language Models
This addresses the challenge of enabling language models to learn new tasks without forgetting previous ones, which is crucial for real-world applications, though it appears incremental as it builds on existing prompt-based methods.
The authors tackled the problem of catastrophic forgetting in continual learning for language models by introducing Progressive Prompts, which learns new soft prompts for each task and concatenates them sequentially while keeping the base model frozen. Their method outperformed state-of-the-art approaches with over 20% improvement in average test accuracy on T5 models.
We introduce Progressive Prompts - a simple and efficient approach for continual learning in language models. Our method allows forward transfer and resists catastrophic forgetting, without relying on data replay or a large number of task-specific parameters. Progressive Prompts learns a new soft prompt for each task and sequentially concatenates it with the previously learned prompts, while keeping the base model frozen. Experiments on standard continual learning benchmarks show that our approach outperforms state-of-the-art methods, with an improvement >20% in average test accuracy over the previous best-preforming method on T5 model. We also explore a more challenging continual learning setup with longer sequences of tasks and show that Progressive Prompts significantly outperforms prior methods.