"reward hacking mitigation" Papers

3 papers found

Filters:reward hacking mitigationClear all

Conference

AAAI 2025 (3,028)CVPR 2025 (2,873)ICCV 2025 (2,701)ICLR 2025 (3,827)ICML 2025 (3,340)ISMAR 2025 (229)NeurIPS 2025 (5,858)AAAI 2024 (2,289)CVPR 2024 (2,716)ECCV 2024 (2,387)ICLR 2024 (2,297)ICML 2024 (2,635)

Paper Type

poster (24,624)paper (8,140)oral (1,594)spotlight (1,421)highlight (975)

RRM: Robust Reward Model Training Mitigates Reward Hacking

Tianqi Liu, Wei Xiong, Jie Ren et al.

ICLR 2025posterarXiv:2409.13156
44
citations

Transforming and Combining Rewards for Aligning Large Language Models

Zihao Wang, Chirag Nagpal, Jonathan Berant et al.

ICML 2024poster

WARM: On the Benefits of Weight Averaged Reward Models

Alexandre Rame, Nino Vieillard, Léonard Hussenot et al.

ICML 2024poster