Summary of Sera: Self-reviewing and Alignment Of Large Language Models Using Implicit Reward Margins, by Jongwoo Ko et al.
SeRA: Self-Reviewing and Alignment of Large Language Models using Implicit Reward Marginsby Jongwoo Ko, Saket…
Summary of Accelerated Preference Optimization For Large Language Model Alignment, by Jiafan He et al.
Accelerated Preference Optimization for Large Language Model Alignmentby Jiafan He, Huizhuo Yuan, Quanquan GuFirst submitted…
Summary of Reward Learning From Preference with Ties, by Jinsong Liu et al.
Reward Learning From Preference With Tiesby Jinsong Liu, Dongdong Ge, Ruihao ZhuFirst submitted to arxiv…
Summary of Seppo: Semi-policy Preference Optimization For Diffusion Alignment, by Daoan Zhang et al.
SePPO: Semi-Policy Preference Optimization for Diffusion Alignmentby Daoan Zhang, Guangchen Lan, Dong-Jun Han, Wenlin Yao,…
Summary of Beyond Bradley-terry Models: a General Preference Model For Language Model Alignment, by Yifan Zhang et al.
Beyond Bradley-Terry Models: A General Preference Model for Language Model Alignmentby Yifan Zhang, Ge Zhang,…
Summary of Evaluating Robustness Of Reward Models For Mathematical Reasoning, by Sunghwan Kim et al.
Evaluating Robustness of Reward Models for Mathematical Reasoningby Sunghwan Kim, Dongjin Kang, Taeyoon Kwon, Hyungjoo…
Summary of The Perfect Blend: Redefining Rlhf with Mixture Of Judges, by Tengyu Xu et al.
The Perfect Blend: Redefining RLHF with Mixture of Judgesby Tengyu Xu, Eryk Helenowski, Karthik Abinav…
Summary of Calibrating Language Models with Adaptive Temperature Scaling, by Johnathan Xie et al.
Calibrating Language Models with Adaptive Temperature Scalingby Johnathan Xie, Annie S. Chen, Yoonho Lee, Eric…
Summary of Hybridflow: a Flexible and Efficient Rlhf Framework, by Guangming Sheng et al.
HybridFlow: A Flexible and Efficient RLHF Frameworkby Guangming Sheng, Chi Zhang, Zilingfeng Ye, Xibin Wu,…
Summary of Vickreyfeedback: Cost-efficient Data Construction For Reinforcement Learning From Human Feedback, by Guoxi Zhang et al.
VickreyFeedback: Cost-efficient Data Construction for Reinforcement Learning from Human Feedbackby Guoxi Zhang, Jiuding DuanFirst submitted…