WPO: Enhancing RLHF with Weighted Preference Optimization
Paper • 2406.11827 • Published • 17
RL
-
-
Self-Improving Robust Preference Optimization
Paper • 2406.01660 • Published • 20 -
Bootstrapping Language Models with DPO Implicit Rewards
Paper • 2406.09760 • Published • 41 -
BPO: Supercharging Online Preference Learning by Adhering to the Proximity of Behavior LLM
Paper • 2406.12168 • Published • 7 -
Understanding and Diagnosing Deep Reinforcement Learning
Paper • 2406.16979 • Published • 10 -
Step-DPO: Step-wise Preference Optimization for Long-chain Reasoning of LLMs
Paper • 2406.18629 • Published • 42 -
Understand What LLM Needs: Dual Preference Alignment for Retrieval-Augmented Generation
Paper • 2406.18676 • Published • 6 -
Step-Controlled DPO: Leveraging Stepwise Error for Enhanced Mathematical Reasoning
Paper • 2407.00782 • Published • 24 -
Direct Preference Knowledge Distillation for Large Language Models
Paper • 2406.19774 • Published • 22 -
Understanding Reference Policies in Direct Preference Optimization
Paper • 2407.13709 • Published • 17 -
Self-Training with Direct Preference Optimization Improves Chain-of-Thought Reasoning
Paper • 2407.18248 • Published • 33 -
JudgeBench: A Benchmark for Evaluating LLM-based Judges
Paper • 2410.12784 • Published • 47