ChatGPT Needs a Chemistry Tutor Too

07 April 2023, Version 1
This content is a preprint and has not undergone peer review at the time of posting.

Abstract

AI and ChatGPT technology have the potential to revolutionize the education sector, and this study aimed to evaluate if prompt formats, response consistency, and reliability of ChatGPT responses could help colleges make the most of this technology. The results of this study can guide future AI and ChatGPT implementations and ensure they are used to their fullest potential. The data does not demonstrate a statistically significant difference between multiple-choice and free response prompt formats. Neither format achieved scores higher than 37%, and testing different locations did not improve scores. Interestingly, ChatGPT's free version provides accurate responses to discipline-specific questions that contain information from unrelated topics, improving its accuracy over the free response questions. However, it's important to remember that while ChatGPT can identify the correct answer within a given context, it may not be able to tell if the answer it chooses is correct computationally or through analysis.

Keywords

Artificial intelligence (AI)
Introductory Chemistry
Chemical education
Large language model (LLM)
Natural language processing (NLP)

Supplementary materials

Title
Description
Actions
Title
ChatGPT Needs a Chemistry Tutor Too
Description
Dataset
Actions

Comments

Comments are not moderated before they are posted, but they can be removed by the site moderators if they are found to be in contravention of our Commenting Policy [opens in a new tab] - please read this policy before you post. Comments should be used for scholarly discussion of the content in question. You can find more information about how to use the commenting feature here [opens in a new tab] .
This site is protected by reCAPTCHA and the Google Privacy Policy [opens in a new tab] and Terms of Service [opens in a new tab] apply.