Reward models trained from pairwise preferences often exploit superficial shortcut cues rather than learning true response quality. We propose DynaCF, a dynamic reweighting framework for mitigating shortcut learning in reward model training.
arXiv:2607. 24484v1 Announce Type: new Abstract: This paper studies what discriminatively trained reward models (RMs) memorize by measuring counterfactual memorization on two human preference datasets.
By Ivo Verhoeven, Pushkar Mishra, Ekaterina Shutova
This paper studies what discriminatively trained reward models (RMs) memorize by measuring counterfactual memorization on two human preference datasets. We show that RMs 1) misallocate memorization to easy, high margin preference pairs, 2) memorize dataset-specific shortcuts (e.
arXiv:2509. 22851v4 Announce Type: replace-cross Abstract: Margin-based optimization is fundamental to improving generalization and robustness in classification tasks.
By Yaswanth Chittepu, Prasann Singhal, Greg Durrett, Scott Niekum
arXiv:2605.16339v2 Announce Type: replace
Abstract: Preference learning in large language models relies on reward models as proxies for human judgment. However, these models frequently exhibit prefer...
By Shunchang Liu, Xin Chen, Belen Martin Urcelay, Francesco Croce
arXiv:2502.14643v3 Announce Type: replace
Abstract: Direct Preference Optimization (DPO) is a widely adopted offline algorithm for preference-based reinforcement learning from human feedback (RLHF),...
By Gengxu Li, Tingyu Xia, Yi Chang, Yuan Wu