A hallmark of modern large language models (LLMs) is their impressive general zero-shot and few-shot abilities, often elicited through prompt-based and/or in-context learning. However, while highly coveted and being the most general, zero-shot performances in LLMs are still typically weaker due to the lack of guidance and the difficulty of applying existing automatic prompt design methods in general tasks when ground-truth labels are unavailable. In this study, we address this by presenting Universal Self-adaptive Prompting (USP), an automatic prompt design approach specifically tailored for zero-shot learning (while compatible with few-shot). Requiring only a small amount of unlabeled data & an inference-only LLM, USP is highly versatile: to achieve universal prompting, USP categorizes a possible NLP task into one of the three possible task types, and then uses a corresponding selector to select the most suitable queries & zero-shot model-generated responses as pseudo-demonstrations, thereby generalizing ICL to the zero-shot setup in a fully automated way. We evaluate zero-shot USP with two PaLM models, and demonstrate performances that are considerably stronger than standard zero-shot baselines and are comparable to or even superior than few-shot baselines across more than 20 natural language understanding (NLU) and natural language generation (NLG) tasks.

通过研究，我们提出了一种自适应提示设计方法，能够使用只有少量未标记的数据和仅推理的LLM实现广泛的零-shot学习，该方法通过将NLP任务分类为三种类型，并使用相应的选择器选择最合适的查询和零-shot模型生成的响应作为伪证明，以完全自动化的方式将ICL推广到零-shot设置，从而呈现与少量-shot基线可比甚至优于的表现。

通用自适应提示