PAGE: Prompt Augmentation for text Generation Enhancement
This addresses the need for more adaptable and efficient text generation in domains like requirements engineering, though it is incremental as it builds on existing prompt augmentation methods.
The paper tackles the problem of poor performance or high data needs in natural language generative models for specific tasks by introducing PAGE, a framework that uses lightweight auxiliary modules to enrich inputs, improving generation quality and controllability, with a proof of concept in software requirements generation.
In recent years, natural language generative models have shown outstanding performance in text generation tasks. However, when facing specific tasks or particular requirements, they may exhibit poor performance or require adjustments that demand large amounts of additional data. This work introduces PAGE (Prompt Augmentation for text Generation Enhancement), a framework designed to assist these models through the use of simple auxiliary modules. These modules, lightweight models such as classifiers or extractors, provide inferences from the input text. The output of these auxiliaries is then used to construct an enriched input that improves the quality and controllability of the generation. Unlike other generation-assistance approaches, PAGE does not require auxiliary generative models; instead, it proposes a simpler, modular architecture that is easy to adapt to different tasks. This paper presents the proposal, its components and architecture, and reports a proof of concept in the domain of requirements engineering, where an auxiliary module with a classifier is used to improve the quality of software requirements generation.