Investigating Automatic Scoring and Feedback using Large Language Models

arXiv:2405.00602v1 Announce Type: cross
Abstract: Automatic grading and feedback have been long studied using traditional machine learning and deep learning techniques using language models. With the recent accessibility to high performing large language models (LLMs) like LLaMA-2, there is an opportunity to investigate the use of these LLMs for automatic grading and feedback generation. Despite the increase in performance, LLMs require significant computational resources for fine-tuning and additional specific adjustments to enhance their performance for such tasks. To address these …

abstract accessibility arxiv cs.cl cs.lg deep learning deep learning techniques feedback language language models large language large language models llama llms machine machine learning scoring traditional machine learning type