Generative AI Series

Based on the success of Professor Christian Terwiesch’s viral paper, Would ChatGPT Get A Wharton MBA?, this series details experiments with generative AI conducted by Professor Terwiesch and colleagues.

Beyond Multiple Choice: The Role of Large Language Models in...

This case study investigates the use of Large Language Models, such as GPT-3 and GPT-4, in enhancing real-time feedback and improving educational simulations for various student cohorts at Wharton.

Unlisted

Reimagining Customer Service Journeys with LLMs: A Framework for...

This paper outlines a framework for integrating large language models (LLMs) into chatbot design to enhance customer service, focusing on five key decision areas for effective implementation.

Unlisted

Prompting Diverse Ideas: Increasing AI Idea Variance

This paper explores methods to enhance the diversity and quality of AI-generated ideas, focusing on the application of different prompting techniques using GPT-4.

Unlisted

Can AI Provide Ethical Advice?

This study examines the effectiveness of AI-based ethical advising using the GPT-4 model, comparing it with human expert advice across diverse groups including online participants, MBA students, and a panel of experts.

Unlisted

Ideas Are Dimes A Dozen: Large Language Models For Idea...

This study compares the ideation capabilities of ChatGPT-4 with those of students from an elite university, highlighting ChatGPT-4's superior performance in generating high-quality, innovative ideas.

Unlisted

Selected ()