Automated Subjective Answer Evaluation using GenAI and NLP by Enhancing Accuracy, Fairness, and Feedback in Education

The problem in subjective evaluation of answer is that the traditional evaluation is not consistent, not fair, and not time efficient. Utilizing Generative AI (GenAI) and Natural Language Processing (NLP), this project presents an innovative technique which automates the evaluation process for subjective answers. It consists of the system that analyzes student’s response using predefined grading rubrics to assign them scores based on quality and relevance and gives them personalized feedback. The system, using a fine tuned GenAI model, reduces human bias and inconsistencies by being nuanced on context and coherence. The system is an easy to use and user friendly tool for Educators to manage and review evaluations through Streamlit hosted system. The solution proposed aims to achieve higher grading accuracy, reduce assessment workflow complexities, while providing perspective that can inform students learning on what is being assessed. The potential applications of this technology are great and include essay grading, peer review and professional training test selection.