Jump to Content

RLHF and IIA: Perverse Incentives

Published
View publication

Abstract

Existing algorithms for reinforcement learning from human feedback (RLHF) can incentivize responses at odds with preferences because they are based on models that assume independence of irrelevant alternatives (IIA). The perverse incentives induced by IIA hinder innovations on query formats and learning algorithms.

Authors

Wanqiao Xu*, Shi Dong, Xiuyuan Lu, Grace Lam, Zheng Wen, Benjamin Van Roy

*
External author

Venue

arXiv