Arena-Hard

Papers using Arena-Hard (12)

References Improve LLM Alignment in Non-Verifiable Domains2026Online Rubrics Elicitation from Pairwise Comparisons2025TGDPO: Harnessing Token-Level Reward Guidance for Enhancing Direct Preference Optimization2025Pretrain Value, Not Reward: Decoupled Value Policy Optimization2025Scalable Reinforcement Post-Training Beyond Static Human Prompts: Evolving Alignment via Asymmetric Self-Play2024The Perfect Blend: Redefining RLHF with Mixture of Judges2024 · 2 citesCritique-out-Loud Reward Models2024 · 1 citesAlphaDPO: Adaptive Reward Margin for Direct Preference Optimization2024Dr. SoW: Density Ratio of Strong-over-weak LLMs for Reducing the Cost of Human Annotation in Preference Tuning2024T-REG: Preference Optimization with Token-Level Reward Regularization2024Segmenting Text and Learning Their Rewards for Improved RLHF in Language Model2025Reward Model Routing in Alignment2025