Please use this identifier to cite or link to this item: https://repository.isls.org/handle/1/13013
Title: Augmenting LLMs with knowledge seeds for clinical question generation
Other Titles: Augmenting LLMs with Knowledge Seeds for Clinical Question Generation
Authors: Kong, Lingchen
Muntean, William
Betts, Joe
Keywords: ICLS
Issue Date: 2026
metadata.dc.format.pagerange: 2660-2662
Publisher: International Society of the Learning Sciences
Citation: Kong, L., Muntean, W., & Betts, J. (2026). Augmenting LLMs with knowledge seeds for clinical question generation. In Litts, B. K., DeLiema, D., Lee, C., Krist, S. Mawasi, A., Martin, L., & Kumpulainen, K. (Eds.), Proceedings of the 20th International Conference of the Learning Sciences - ICLS 2026 (pp. 2660-2662). International Society of the Learning Sciences.
Series/Report no.: Proceedings of the 20th International Conference of the Learning Sciences - ICLS 2026
Abstract: High-stakes clinical assessments require complex, context-rich items that test applied reasoning but are time-consuming to create. This study presents a learning-centered LLM pipeline that generates multiple-choice clinical items using knowledge seeds from validated item banks. The LLM-generated Multiple Choice (MC) items demonstrated comparable option-level ecological validity and distractor plausibility to expert-created items, with the pipeline facilitating item development and accelerating the refresh cycle to maintain item bank integrity.
Description: POSTER
URI: https://doi.org/10.22318/icls2026.742190
https://repository.isls.org/handle/1/13013
ISBN: 979-8-9906980-7-9
ISSN: 1819-0138
Appears in Collections:ISLS Annual Meeting 2026

Files in This Item:
File SizeFormat 
ICLS2026_2660-2662.pdf313.17 kBAdobe PDFView/Open


Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.