Prompt-and-Rerank: A Method for Zero-Shot and Few-Shot Arbitrary Textual Style Transfer with Small Language Models (2205.11503v1)

Abstract: We propose a method for arbitrary textual style transfer (TST)--the task of transforming a text into any given style--utilizing general-purpose pre-trained LLMs. Our method, Prompt-and-Rerank, is based on a mathematical formulation of the TST task, decomposing it into three constituent components: textual similarity, target style strength, and fluency. Specifically, our method first uses zero-shot or few-shot prompting to obtain a set of candidate generations in the target style, and then re-ranks these candidates according to a combination of the three components above. Empirically, our method enables small pre-trained LLMs to perform on par with state-of-the-art large-scale models while consuming two orders of magnitude less compute and memory. Finally, we conduct a systematic investigation of the effect of model size and prompt design (e.g., prompt paraphrasing and delimiter-pair choice) on style transfer quality across seven diverse textual style transfer datasets.