AI-driven education: a comparative study on ChatGPT and Bard in supply chain management contexts

Abstract

This study conducts a comparative analysis of two prominent generative artificial intelligence (GAI) tools, ChatGPT and Bard, specifically in the context of supply chain management. Using a dataset of 150 certified supply chain professional questions, the models are evaluated on the basis of accuracy, relevance, and clarity, and t tests are employed to assess differences between the tools. ChatGPT outperforms Bard in both accuracy and relevance, with statistically significant results, whereas Bard demonstrated a slight edge in readability, scoring higher on the Flesch readability ease scale. Both models exhibited moderate to high cosine similarity for the majority of the questions, indicating closely aligned outputs. However, variations in their performance arose from differences in their underlying architectures – ChatGPT’s iterative improvement process balances utility and safety, whereas Bard is designed with stricter safeguards to minimize misuse. These findings have important implications for the integration of GAI tools in educational settings, such as developing supply chain curricula and training materials requiring high accuracy and relevance. Additionally, the results suggest broader applications of the GAI in supply chain decision-making, operational efficiency improvements, and enhanced stakeholder communication. The study also highlights the importance of continuous model adaptation to ensure the ethical, safe, and effective use of AI technologies in professional settings. Future research could explore how real-time feedback loops impact AI performance and how diverse training datasets influence model accuracy and relevance across different industries, further advancing the role of AI in complex domains such as supply chain management.

Keywords

• Supply chain
• logistics
• LLM
• ChatGPT
• Bard
• readability