Soft prompt tuning is a parameter-efficient technique for adapting a large language model to a task by learning additional prompt embeddings. It avoids updating most or all model weights and instead optimizes continuous prompt representations through training.
A technique for tuning a large language model for a particular task, without resource intensive fine-tuning. Instead of retraining all the weights in the model, soft prompt tuning automatically adjusts a prompt to achieve the same goal. Given a textual prompt, soft prompt tuning typically appends additional token embeddings to the prompt and uses backpropagation to optimize the input. A "hard" prompt contains actual tokens instead of token embeddings.