Hugging Face Trending Papers

DynaCF: Mitigating Shortcut Learning in Reward Models via Dynamic Counterfactual Sensitivity

Read the original on Hugging Face Trending Papers →

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.

Summary generated by The Flow from the publisher's feed. The full article lives at Hugging Face Trending Papers.

Hugging Face Trending Papers
Jul 27

What do Reward Models Memorize?

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 Machine Learning
Jul 28

What do Reward Models Memorize?

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