论文标题
在零摄像语言样式上的语言模型的可扩展提示自定义
Extensible Prompts for Language Models on Zero-shot Language Style Customization
论文作者
论文摘要
我们提出了可扩展的提示（X-Prompt），以提示自然语言（NL）以外的大型语言模型（LLM）。 X-Prompt不仅指示NL的LLM，而且还指导一个虚构单词的可扩展词汇。注册新的假想单词使我们能够指导LLM理解难以用NL单词描述的概念，从而使及时描述性。同样，这些虚构的单词被设计为稳健的分布（OOD），以便可以在各种提示中像NL单词一样使用，将X-Prompt与软提示区分开，该提示与拟合分配数据的数据相吻合。我们建议以上下文启动的学习（CAL）来学习虚构的单词，以实现一般可用性，从而使它们能够在OOD（看不见）提示中正常工作。我们试验X-Prompt以零摄像的语言样式自定义作为案例研究。 X-Prompt的有希望的结果表明，其潜力有助于促进自然语言界面以外的高级互动，从而弥合了人类与LLM之间的通信差距。
We propose eXtensible Prompt (X-Prompt) for prompting a large language model (LLM) beyond natural language (NL). X-Prompt instructs an LLM with not only NL but also an extensible vocabulary of imaginary words. Registering new imaginary words allows us to instruct the LLM to comprehend concepts that are difficult to describe with NL words, thereby making a prompt more descriptive. Also, these imaginary words are designed to be out-of-distribution (OOD) robust so that they can be (re)used like NL words in various prompts, distinguishing X-Prompt from soft prompt that is for fitting in-distribution data. We propose context-augmented learning (CAL) to learn imaginary words for general usability, enabling them to work properly in OOD (unseen) prompts. We experiment X-Prompt for zero-shot language style customization as a case study. The promising results of X-Prompt demonstrate its potential to facilitate advanced interaction beyond the natural language interface, bridging the communication gap between humans and LLMs.
