Reducing Retraining by Recycling Parameter-Efficient Prompts. (arXiv:2208.05577v1 [cs.CL])

Parameter-efficient methods are able to use a single frozen pre-trained large
language model (LLM) to perform many tasks by learning task-specific soft
prompts that modulate model behavior when concatenated to the input text.
However, these learned prompts are tightly coupled to a given frozen model --
if the model is updated, corresponding new prompts need to be obtained. In this
work, we propose and investigate several approaches to "Prompt Recycling'"
where a prompt trained on a source model is transformed …

arxiv recycling