Taichiro Endo. Vertical Moral Growth for Robust Alignment: Perspective-Based Fine-Tuning Reduces Deception in Large Language Models. In Marija Slavkovik 0001, Hiroshi Yamakawa, Rafal Rzepka, Taichiro Endo, Louise A. Dennis, Raynaldio Limarga, Michael Fisher 0001, Ryutaro Ichise, editors, Proceedings of the Machine Ethics: from formal methods to emergent machine ethics Workshop (MEW 2026) co-located with the 40th Annual AAAI Conference on Artificial Intelligence (AAAI 2026), Singapore, January 27, 2026. Volume 4189 of CEUR Workshop Proceedings, pages 48-60, CEUR-WS.org, 2026. [doi]
Abstract is missing.