FORSBERG, Linnea. Instruction Alignment and Risk Calibration in Large Language Models for Safe Human-AI Interaction. Journal of Computer Technology and Software, [S. l.], v. 4, n. 6, 2025. DOI: 10.5281/zenodo.15809635. DisponÃvel em: https://www.ashpress.org/index.php/jcts/article/view/182. Acesso em: 9 aug. 2025.