Can Large Language Models Automatically Score Proficiency of Written Essays?

arXiv:2403.06149v1 Announce Type: new
Abstract: Although several methods were proposed to address the problem of automated essay scoring (AES) in the last 50 years, there is still much to desire in terms of effectiveness. Large Language Models (LLMs) are transformer-based models that demonstrate extraordinary capabilities on various tasks. In this paper, we test the ability of LLMs, given their powerful linguistic knowledge, to analyze and effectively score written essays. We experimented with two popular LLMs, namely ChatGPT and Llama. We …

abstract arxiv automated capabilities cs.ai cs.cl essay language language models large language large language models llms scoring tasks terms transformer type