What type of study is this?

This is a Experimental Study study (also classified as: Quantitative Study).

September 19, 2025Open Access

Optimizing GPT-Based Distractor Generation for the Korean CSAT English Exam

View Full Paper

Ask AI

Bookmark

Authors

Automated distractor generation enhances Korean CSAT exam items, suggesting improvements for language assessment.

Automated distractor generation achieves improved alignment with real exam items, enhancing assessment quality.
Fine-tuning yielded the best results, with the highest semantic alignment observed in a test of 80 CSAT items.
Approaches like in-context learning showed effectiveness in creating realistic distractors for classroom settings.
Integrating educational scaffolding theories into distractor generation results in better understanding of student misconceptions.

Jung et al. (2025) studied this question.

View Full Paper

Ask AI

Bookmark

September 19, 2025Open Access

View Full Paper

Ask AI

Bookmark

Authors

Automated distractor generation enhances Korean CSAT exam items, suggesting improvements for language assessment.

Automated distractor generation achieves improved alignment with real exam items, enhancing assessment quality.
Fine-tuning yielded the best results, with the highest semantic alignment observed in a test of 80 CSAT items.
Approaches like in-context learning showed effectiveness in creating realistic distractors for classroom settings.
Integrating educational scaffolding theories into distractor generation results in better understanding of student misconceptions.

Jung et al. (2025) studied this question.

View Full Paper

Ask AI

Bookmark