Student Answer Script Evaluation Using Large Language Model
Hrithik M Joseph, S Aishwarya, Sriga, Harish Khumar · 2024
This research proposes a novel approach to assess the quality of summaries written by students. This will assist teachers in evaluating the quality of student summaries and also help learning platforms provide immediate feedback to students. Evaluating summaries introduces an added layer of complexity, where models must consider both the student's context and the actual text. Although there are a handful of current techniques for summary evaluation, these models have often focused on assessing automatically-generated summaries rather than real student writing. Students rarely have enough opportunities to practice this skill, as evaluating and providing feedback on summaries can be a time-intensive process for teachers. Large Language Models are foundational machine learning models that use deep learning algorithms to process and understand natural language. These models are trained on massive amounts of text data to learn patterns and entity relationships in the language. Students will have more opportunities to practice summarizing, while simultaneously improving their reading comprehension.