Understanding the Role of Temperature in Diverse Question Generation by GPT-4
This incremental work addresses the problem of controlling output diversity in AI-generated educational content for researchers and practitioners.
The study investigated how GPT-4's temperature parameter affects question generation diversity, finding that higher temperatures significantly increase diversity and reveal different similarity types, with particular difficulty in generating diverse questions for lower Bloom's Taxonomy levels.
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.