Prompt engineering for single-best-answer multiple-choice questions in licensing examinations: a narrative review with a case study involving the Korean Medical Licensing Examination.
The emergence of large language models (LLMs) has generated growing interest in their potential applications for medical assessment and item development. This practice-oriented narrative review examines the potential of LLMs, particularly ChatGPT, for generating and validating single-best-answer mul...
| Published in: | Journal of Educational Evaluation for Health Professions Vol. 22; pp. 1 - 16 |
|---|---|
| Main Authors: | , , , |
| Format: | case study review Journal Article |
| Published: |
National Health Personnel Licensing Examination Board
2025
|
| Online Access: | View this record in EBSCOhost |