rm-robustness/ultrafeedback-train
Viewer
•
Updated
•
51.2k
•
8
[ICML 2025] Robustness in RMs
Dataset and reward models for "On the Robustness of Reward Models for Language Model Alignment (ICML 2025)"
-
-
rm-robustness/ultrafeedback-valid-1-in-domain
Viewer • Updated • 51.2k • 8 -
rm-robustness/ultrafeedback-valid-2-prompt-ood
Viewer • Updated • 11.1k • 6 -
rm-robustness/ultrafeedback-valid-3-response-ood
Viewer • Updated • 51.2k • 3 -
rm-robustness/ultrafeedback-valid-4-mutual-ood
Viewer • Updated • 11.1k • 9 -
rm-robustness/L31-8B-SKPv2-BSR-1e2
Text Classification • 8B • Updated • 3 -
rm-robustness/L31-8B-SKPv2-BSR-1e3
Text Classification • 8B • Updated • 3 -
rm-robustness/L31-8B-SKPv2-BSR-1e4
Text Classification • 8B • Updated • 8