Date
Publisher
arXiv
We evaluate the effectiveness of GPT-4 Turbo in generating educational
questions from NCERT textbooks in zero-shot mode. Our study highlights GPT-4
Turbo's ability to generate questions that require higher-order thinking
skills, especially at the "understanding" level according to Bloom's Revised
Taxonomy. While we find a notable consistency between questions generated by
GPT-4 Turbo and those assessed by humans in terms of complexity, there are
occasional differences. Our evaluation also uncovers variations in how humans
and machines evaluate question quality, with a trend inversely related to
Bloom's Revised Taxonomy levels. These findings suggest that while GPT-4 Turbo
is a promising tool for educational question generation, its efficacy varies
across different cognitive levels, indicating a need for further refinement to
fully meet educational standards.
Study at a glance
- Question: How well can GPT-4 Turbo generate school questions from textbooks across different thinking levels?
- Setting and data: NCERT school textbooks.
- Method: Comparison of AI-generated questions and machine evaluations with human assessments.
Why it matters
Evaluating the effectiveness of GPT-4 Turbo in generating school-level educational questions from textbooks in zero-shot mode addresses how the tool performs across the different cognitive levels of Bloom's Revised Taxonomy.
Key findings
- Using NCERT textbooks, GPT-4 Turbo generated questions requiring higher-order thinking skills, especially at the "understanding" level of Bloom's Revised Taxonomy.
- The complexity of AI-generated questions was notably consistent with human assessments, although occasional differences occurred.
- Human and machine evaluations of question quality diverged, showing a pattern inversely related to Bloom's Revised Taxonomy levels.
Summary drafted with AI from the paper’s abstract and may contain errors. See the full paper for details.
What is the application?
Who is the user?
Who age?
Why use AI?
Study design
