Research on AI-Powered Essay Writing Assistant with Contextual Revision System

This report presents an AI-powered essay writing assistant that combines three advanced modules: a fine-tuned DeepSeek-R1-Distill-Llama-8B language model for contextual revisions, retrieval-augmented generation (RAG) for evidence-based suggestions, and a DeBERTaV3-based ordinal regression model for essay scoring. By combining the two models, the system demonstrates high grammatical accuracy in revisions and achieves a satisfactory value of quadratic weighted Kappa in scoring while providing detailed suggestions for further improvement, significantly outperforming baseline approaches. Through systematic integration of these components, the writing assistant offers holistic writing support while maintaining computational efficiency. It can provide real-time feedback, contextual suggestions, and rubric-aligned scoring, significantly enhancing the writing process as well as the user experience. The work may offer a method of using AI techniques in essay writing, demonstrating how context-aware systems can enhance writing quality while maintaining computational practicality. By streamlining the writing and grading processes, this project has the potential to boost productivity and improve learning outcomes, making it a valuable tool in modern educational environments.