LAMBERT, Pierre; ERIKSEN, Maja. Reward Modeling from Human Feedback Improves Controllability in Large Generative Models. International Journal of Advanced Engineering and Technology Research, [S. l.], v. 2, n. 1, p. 13–19, 2026. DOI: 10.54097/z5t42855. Disponível em: https://ijaetr.org/index.php/ojs/article/view/85. Acesso em: 28 jul. 2026.