RewardBench

Papers using RewardBench (13)

PaTaRM: Bridging Pairwise and Pointwise Signals via Preference-Aware Task-Adaptive Reward Modeling2025 · 4 citesIRPM: Intergroup Relative Preference Modeling for Pointwise Generative Reward Models2026Tiny Reward Models2025Efficient Online RFT with Plug-and-Play LLM Judges: Unlocking State-of-the-Art Performance2025Intra-Trajectory Consistency for Reward Modeling2025Critique-out-Loud Reward Models2024 · 1 citesPost-hoc Reward Calibration: A Case Study on Length Bias2024 · 1 citesQuantile Regression for Distributional Reward Models in RLHF2024Evaluating Robustness of Reward Models for Mathematical Reasoning2024Dr. SoW: Density Ratio of Strong-over-weak LLMs for Reducing the Cost of Human Annotation in Preference Tuning2024Act-Adaptive Margin: Dynamically Calibrating Reward Models for Subjective Ambiguity2025Multi-Agent Collaborative Reward Design for Enhancing Reasoning in Reinforcement Learning2025Sentence-level Reward Model can Generalize Better for Aligning LLM from Human Preference2025