In a 21-educator study, GPT-3.5 generated the best-rated multiple-choice questions from a provided source text, beating Llama 2 and Mistral on most metrics, though learning utility was not significantly different.
A taxonomy for learning, teaching, and assessing: A revision of bloom's taxonomy of educational objectives: complete edition, 2001
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CL 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Multiple-Choice Question Generation Using Large Language Models: Methodology and Educator Insights
In a 21-educator study, GPT-3.5 generated the best-rated multiple-choice questions from a provided source text, beating Llama 2 and Mistral on most metrics, though learning utility was not significantly different.