Understanding the Role of Temperature in Diverse Question Generation by GPT-4
Open Access
- 14 March 2024
- conference paper
- Published by Association for Computing Machinery (ACM)
- p. 1550-1551
Abstract
We conduct a preliminary study of the effect of GPT's temperature parameter on the diversity of GPT4-generated questions. We find that using higher temperature values leads to significantly higher diversity, with different temperatures exposing different types of similarity between generated sets of questions. We also demonstrate that diverse question generation is especially difficult for questions targeting lower levels of Bloom's Taxonomy.Keywords
All Related Versions
This publication has 4 references indexed in Scilit:
- A Comparative Study of AI-Generated (GPT-4) and Human-crafted MCQs in Programming Education2024
- Generating CS1 Coding Questions using OpenAI2023
- Experiences from Using Code Explanations Generated by Large Language Models in a Web Software Development E-Book2023
- The Measurement of Observer Agreement for Categorical DataBiometrics, 1977