Explanations generated from generic questions were rated significantly better than those generated from random questions, supporting the hypothesis that question selection strategy matters¶

Claim · All claims
Evidence · 1 study · causal r2 · q3
Currency · newest study 2024 · not yet checked against its sources · not reviewed by a person

Subclaims¶

q3 i? Generic-question explanations outperformed random-question explanations, giving further evidence for the validity of the hypothesis that useful implicit questions are those best answered by the collection. → Sovrano Francesco 2024

Evidence¶

Sovrano Francesco 2024¶

Sovrano Francesco, Ashley Kevin, Brusilovsky Peter Leonid, Vitali Fabio. (2024). How to Improve the Explanatory Power of an Intelligent Textbook: a Case Study in Legal Writing. International Journal of Artificial Intelligence in Education. https://doi.org/10.1007/s40593-024-00399-w

q3 · i? · causal · r2

Same within-subjects user study (more than 100 students rating explanations on a 0-to-5-star scale) comparing the YAI4Hu generic overview generator against the random-question explainer. The article reports the difference as significant without printing a test statistic or effect size.

"Notably, the results also show that the explanations generated from generic questions are significantly better than those generated from random questions, giving further evidence in support of the validity of the hypothesis."

Discussion¶

Related Claims¶

• A DoX-based pre-filtering step reduces the Intelligent Explanation Generator's asymptotic time complexity from quadratic to linear in the size of the text collection — related
• In a within-subjects user study with more than 100 students, explanations generated by the Intelligent Explanation Generator were rated significantly higher than those of random-question and generic-question baselines — related
• Teaching (writing a verbatim lecture script) produces better create question generation than explaining (writing a textbook explanation) — related