Task Prompt Vectors: Effective Initialization through Multi-Task Soft-Prompt Transfer
This work addresses the problem of inefficient multi-task training in prompt tuning for NLP researchers and practitioners, offering an incremental improvement over existing methods.
The paper tackles the issue of multi-task modularity in soft-prompt tuning for large language models by introducing Task Prompt Vectors, which enable effective initialization and arithmetic operations across tasks, achieving competitive performance on 12 NLU datasets.
Prompt tuning is an efficient solution for training large language models (LLMs). However, current soft-prompt-based methods often sacrifice multi-task modularity, requiring the training process to be fully or partially repeated for each newly added task. While recent work on task vectors applied arithmetic operations on full model weights to achieve the desired multi-task performance, a similar approach for soft-prompts is still missing. To this end, we introduce Task Prompt Vectors, created by element-wise difference between weights of tuned soft-prompts and their random initialization. Experimental results on 12 NLU datasets show that task prompt vectors can be used in low-resource settings to effectively initialize prompt tuning on similar tasks. In addition, we show that task prompt vectors are independent of the random initialization of prompt tuning on 2 different language model architectures. This allows prompt arithmetics with the pre-trained vectors from different tasks. In this way, we provide a competitive alternative to state-of-the-art baselines by arithmetic addition of task prompt vectors from multiple tasks.