This paper utilizes a prompt pool to leverage task-specific knowledge and generate instance-specific prompts using attention mechanisms.

Additionally, it introduces a novel soft verbalizer (RepVerb) that directly constructs label embeddings from feature embeddings.

MetaPrompter offers parameter efficiency, requiring only tuning of the prompt pool.

Powerpoint for this talk

Reference Paper

• MetaPrompting: Learning to Learn Better Prompts
• Model-agnostic meta-learning for fast adaptation of deep networks