Abstract
This study evaluates the potential and challenges of large langue models (LLMs) for education in chemistry. Specifically, we analyze the performance of two state -of-the art of LLMs, ChatGPT and Microsoft Bing AI Chat, on a quiz dataset consisting of 200 multiple-choice questions in chemistry at the high school level. The results show that ChatGPT and Microsoft Bing AI Chat have limitations in answering questions at the application and high application levels. We also compare the scores of the LLMs models with Vietnamese students, indicating that their performance is still lower than the ability of Vietnamese students. The findings suggest that LLMs have great potential in assisting learning and teaching, but further development is needed to improve their ability to solve complex questions at the high application level.
Supplementary weblinks
Title
VNHSGE chemistry dataset
Description
The chemistry dataset consists of 2000 multiple-choice questions designed for the high school level where the evaluation set contains 200 multiple-choice questions. The dataset will be regularly updated to align with the Vietnamese national high school graduation examination, reflecting the changes and content covered in the exam each year. This ensures that the dataset remains relevant and up-to-date for educational purposes and assessment.
Actions
View