Real Customization or Just Marketing: Are Customized Versions of Generative AI Useful?
Open Access
- 17 October 2024
- journal article
- Published by F1000 Research Ltd in F1000Research
- Vol. 13, 791
Abstract
Background Large Language Models (LLMs), as in the case of OpenAITM ChatGPT-4TM Turbo, are revolutionizing several industries, including higher education. In this context, LLMs can be personalised through customization process to meet the student demands on every particular subject, like statistics. Recently, OpenAI launched the possibility of customizing their model with a natural language web interface, enabling the creation of customised GPT versions deliberately conditioned to meet the demands of a specific task. Methods This preliminary research aims to assess the potential of the customised GPTs. After developing a Business Statistics Virtual Professor (BSVP), tailored for students at the Universidad Pontificia Comillas, its behaviour was evaluated and compared with that of ChatGPT-4 Turbo. Firstly, each professor collected 15-30 genuine student questions from “Statistics and Probability” and “Business Statistics” courses across seven degrees, primarily from second-year courses. These questions, often ambiguous and imprecise, were posed to ChatGPT-4 Turbo and BSVP, with their initial responses recorded without follow-ups. In the third stage, professors blindly evaluated the responses on a 0-10 scale, considering quality, depth, and personalization. Finally, a statistical comparison of the systems’ performance was conducted. Results The results lead to several conclusions. Firstly, a substantial modification in the style of communication was observed. Following the instructions it was trained with, BSVP responded in a more relatable and friendly tone, even incorporating a few minor jokes. Secondly, when explicitly asked for something like, “I would like to practice a programming exercise similar to those in R practice 4,” BSVP could provide a far superior response. Lastly, regarding overall performance, quality, depth, and alignment with the specific content of the course, no statistically significant differences were observed in the responses between BSVP and ChatGPT-4 Turbo. Conclusions It appears that customised assistants trained with prompts present advantages as virtual aids for students, yet they do not constitute a substantial improvement over ChatGPT-4 Turbo.Keywords
Funding Information
- Universidad Pontificia Comillas (PP2023_1)
- Santalucía Chair of Analytics for Education
This publication has 21 references indexed in Scilit:
- ChatGPT: Advancing Education with Virtual Assistants2024
- Large Language Model‐Based Chatbots in Higher EducationAdvanced Intelligent Systems, 2024
- Improving elementary EFL speaking skills with generative AI chatbots: Exploring individual and paired interactionsComputers & Education, 2024
- Teaching and testing in the era of text-generative AI: exploring the needs of students and teachersInformation and Learning Sciences, 2024
- ChatGPT for Education and Research: Opportunities, Threats, and StrategiesApplied Sciences, 2023
- ChatGPT for good? On opportunities and challenges of large language models for educationLearning and Individual Differences, 2023
- Chatting and cheating: Ensuring academic integrity in the era of ChatGPTInnovations in Education and Teaching International, 2023
- Is using ChatGPT cheating, plagiarism, both, neither, or forward thinking?Patterns, 2023
- Natural Language Processing2020
- Campus?based university students’ use of dialogueStudies in Higher Education, 2006