Reasoning Processes and Logical Errors of Large Language Models on Koryo Dynasty Questions : A Comparative Analysis of GPT, DeepSeek, and EXAONE Responses to the CSAT
The Journal of Korean Medieval History · 28.02.2026 · 84 · 237-282
DOI: 10.35863/jkmh.84.7 ↗Kurz gefasst
Fachartikel in der Zeitschrift The Journal of Korean Medieval History, online erschienen am 28.02.2026. Verfasst von SooChan Park.
Abstract (Originalsprache)
Kein Abstract verfügbar.
Zitieren
APA
Park, S. (2026). Reasoning Processes and Logical Errors of Large Language Models on Koryo Dynasty Questions : A Comparative Analysis of GPT, DeepSeek, and EXAONE Responses to the CSAT. The Journal of Korean Medieval History, 84(0), 237-282. https://doi.org/10.35863/jkmh.84.7
Vancouver
Park S. Reasoning Processes and Logical Errors of Large Language Models on Koryo Dynasty Questions : A Comparative Analysis of GPT, DeepSeek, and EXAONE Responses to the CSAT. The Journal of Korean Medieval History. 2026;84(0):237-282. doi:10.35863/jkmh.84.7
BibTeX
@article{Park2026,
author = {Park, SooChan},
title = {Reasoning Processes and Logical Errors of Large Language Models on Koryo Dynasty Questions : A Comparative Analysis of GPT, DeepSeek, and EXAONE Responses to the CSAT},
journal = {The Journal of Korean Medieval History},
year = {2026},
volume = {84},
number = {0},
pages = {237--282},
doi = {10.35863/jkmh.84.7}
}
EUVIMED