RRM: Robust Reward Model Training Mitigates Reward Hacking
Tian-Qi Liu, Wei Xiong, Jie Ren, Li-Chang Chen +14 more
2024International Conference on Learning Representations84 citations
Semantic Scholar
Researcher profile · Semantic Scholar
Tian-Qi Liu, Wei Xiong, Jie Ren, Li-Chang Chen +14 more
Scott Sussex, Pier Giuseppe Sessa, A. Makarova, A. Krause
K. Danilov, D. Bansal, Ivan Valiev, V. Kushnarev +11 more