Adaptive In-Context Learning in Large Language Models: A Zero-Leakage Benchmark Using Fictionalized Extensions of the Khom Thai Script. International Journal of Deep Tech in Medical Science and Technology, [S. l.], v. 1, n. 1, 2026. DOI: 10.52939/2krr8t16. Disponível em: https://dtmst.e-geoinfo.com/index.php/dtmst/article/view/14. Acesso em: 4 nov. 2026.