This paper introduces a novel perspective on the automated essay scoring (AES) task, challenging the conventional view of the ASAP dataset as a static entity. Employing simple text denoising techniques using prompting, we explore the dynamic potential within the dataset. While acknowledging the previous emphasis on building regression systems, our paper underscores how making minor changes to a dataset through text denoising can enhance the final results. Text denoising is a crucial step in natural language processing (NLP) and text analysis tasks (Sun & Jiang, 2019; Xian et al., 2021). One of its major applications is in optical character recognition (OCR).