by , ,
Reference:
Stackelberg Learning from Human Feedback: Preference Optimization as a Sequential Game B. Pásztor, T. K. Buening, A. KrauseIn The Fourteenth International Conference on Learning Representations, 2026
Bibtex Entry:
@inproceedings{pasztor2026stackelberg,
	author = {Barna P{\'a}sztor and Thomas Kleine Buening and Andreas Krause},
	booktitle = {The Fourteenth International Conference on Learning Representations},
	title = {Stackelberg Learning from Human Feedback: Preference Optimization as a Sequential Game},
	year = {2026}}