论文标题
朝着人类可读的提示调整：库布里克（Kubrick）的《闪亮》（The Shining）是一部好电影，也是一个很好的提示吗？
Toward Human Readable Prompt Tuning: Kubrick's The Shining is a good movie, and a good prompt too?
论文作者
论文摘要
大型语言模型可以以零拍的方式执行新任务，因为自然语言提示可以指定所需的行为。这些提示通常是手工设计的，但也可以通过标记数据的基于梯度的方法来学习。但是，尤其是在提示是自然语言的情况下，尤其是在提示有效的因素时，这是什么因素。在本文中，我们研究了通过有效提示共享的共同属性。我们首先提出了一种基于Langevin Dynamics的人类可读的及时调整方法（F Luent P ROMPT），该动力学结合了流利的限制，以找到有效和流利的提示的各种分布。我们的分析表明，有效的提示与任务域局部相关，并校准标签单词的先前概率。基于这些发现，我们还提出了一种仅使用未标记数据生成提示的方法，在三个任务中平均比强基础的精度平均优于7.0％。
Large language models can perform new tasks in a zero-shot fashion, given natural language prompts that specify the desired behavior. Such prompts are typically hand engineered, but can also be learned with gradient-based methods from labeled data. However, it is underexplored what factors make the prompts effective, especially when the prompts are natural language. In this paper, we investigate common attributes shared by effective prompts. We first propose a human readable prompt tuning method (F LUENT P ROMPT) based on Langevin dynamics that incorporates a fluency constraint to find a diverse distribution of effective and fluent prompts. Our analysis reveals that effective prompts are topically related to the task domain and calibrate the prior probability of label words. Based on these findings, we also propose a method for generating prompts using only unlabeled data, outperforming strong baselines by an average of 7.0% accuracy across three tasks.
