RewardBench

Papers using RewardBench (15)

PaTaRM: Bridging Pairwise and Pointwise Signals via Preference-Aware Task-Adaptive Reward Modeling2025 · 4 citesNine Judges, Two Effective Votes: Correlated Errors Undermine LLM Evaluation Panels2026CDRRM: Contrast-Driven Rubric Generation for Reliable and Interpretable Reward Modeling2026SCOPE: Selective Conformal Optimized Pairwise LLM Judging2026SR-GRPO: Stable Rank as an Intrinsic Geometric Reward for Large Language Model Alignment2025Explicit Reasoning Makes Better Judges: A Systematic Study on Accuracy, Efficiency, and Robustness2025Intra-Trajectory Consistency for Reward Modeling2025Robust Reward Modeling via Causal Rubrics2025Time To Impeach LLM-as-a-Judge: Programs are the Future of Evaluation2025ENCORE: Entropy-guided Reward Composition for Multi-head Safety Reward Models2025Sentence-level Reward Model can Generalize Better for Aligning LLM from Human Preference2025IPO: Your Language Model is Secretly a Preference Classifier2025Data-adaptive Safety Rules for Training Reward Models2025Margin Matching Preference Optimization: Enhanced Model Alignment with Granular Feedback2024Uncertainty-aware Reward Model: Teaching Reward Models to Know What is Unknown2024