StablePT: Towards Stable Prompting for Few-shot Learning via Input Separation

arXiv:2404.19335v1 Announce Type: new
Abstract: Large language models have shown their ability to become effective few-shot learners with prompting, revoluting the paradigm of learning with data scarcity. However, this approach largely depends on the quality of prompt initialization, and always exhibits large variability among different runs. Such property makes prompt tuning highly unreliable and vulnerable to poorly constructed prompts, which limits its extension to more real-world applications. To tackle this issue, we propose to treat the hard prompt and soft …

abstract arxiv become cs.cl data few-shot few-shot learning however language language models large language large language models paradigm prompt prompting property quality type via