Investigating the Efficacy of Large Language Models in Reflective Assessment Methods through Chain of Thoughts Prompting

TL;DR

This study evaluates the effectiveness of large language models, especially ChatGPT, in grading reflective essays for medical students using Chain of Thought prompting to enhance reasoning skills.

Contribution

It introduces a method for instructing large models to evaluate essays and demonstrates the use of Chain of Thought prompting for this task.

Findings

ChatGPT achieved the highest Cohen kappa score of 0.53.

Llama-7b performed the least effectively with the highest mean squared error.

Models prioritize user privacy by allowing conversation deletion.

Abstract

Large Language Models, such as Generative Pre-trained Transformer 3 (aka. GPT-3), have been developed to understand language through the analysis of extensive text data, allowing them to identify patterns and connections between words. While LLMs have demonstrated impressive performance across various text-related tasks, they encounter challenges in tasks associated with reasoning. To address this challenge, Chain of Thought(CoT) prompting method has been proposed as a means to enhance LLMs' proficiency in complex reasoning tasks like solving math word problems and answering questions based on logical argumentative reasoning. The primary aim of this research is to assess how well four language models can grade reflective essays of third-year medical students. The assessment will specifically target the evaluation of critical thinking skills using CoT prompting. The research will provide the following contributions; to introduce and educate on the process of instructing models to evaluate reflective essays from a dataset they have not been previously trained on; to illustrate the use of CoT prompting as an instructional approach for training large models to carry out particular tasks. Our results suggest that among all the models, Llama-7b performs the least effectively, displaying the highest mean squared error. Conversely, ChatGPT emerges as the superior model, boasting a higher Cohen kappa score value of 0.53. Lastly, it's important to note that the selected models do prioritise user privacy by allowing users to delete their own conducted conversations.