1 citations · 1 across the 2 of their papers we have counts for
2 papers
cs.CV2024
Spectrum AUC Difference (SAUCD): Human-aligned 3D Shape Evaluation
Tianyu Luan, Zhong Li, Lele Chen +4
Existing 3D mesh shape evaluation metrics mainly focus on the overall shape but are usually less sensitive to local details. This makes them inconsistent with human evaluation, as…
cs.LG2024★ 1 cited
ODIN: Disentangled Reward Mitigates Hacking in RLHF
Lichang Chen, Chen Zhu, Davit Soselia +6
In this work, we study the issue of reward hacking on the response length, a challenge emerging in Reinforcement Learning from Human Feedback (RLHF) on LLMs. A well-formatted, verb…