reward model

RLHF Algorithms Ranked: An Extensive Evaluation Across Diverse Tasks, Rewards, and Hyperparameters EMNLP 2025 RLKGF: Reinforcement Learning from Knowledge Graph Feedback Without Human Annotations ACL 2025 RLTHF: Targeted Human Feedback for LLM Alignment ICML 2025 RMB: Comprehensively benchmarking reward models in LLM alignment ICLR 2025 RM-Bench: Benchmarking Reward Models of Language Models with Subtlety and Style ICLR 2025 RPO: Retrieval Preference Optimization for Robust Retrieval-Augmented Generation ACL 2025 RRM: Robust Reward Model Training Mitigates Reward Hacking ICLR 2025 RTTC: Reward-Guided Collaborative Test-Time Compute EMNLP 2025 RuleAdapter: Dynamic Rules for training Safety Reward Models in RLHF ICML 2025 Sample Efficient Alignment Learning With Episodic Control EMNLP 2025 Scalable Ranked Preference Optimization for Text-to-Image Generation ICCV 2025 Science-T2I: Addressing Scientific Illusions in Image Synthesis CVPR 2025 SEAL: Systematic Error Analysis for Value ALignment AAAI 2025 Seeing Eye to AI: Human Alignment via Gaze-Based Response Rewards for Large Language Models ICLR 2025 Self-Consistency Preference Optimization ICML 2025 SELF-EVOLVED REWARD LEARNING FOR LLMS ICLR 2025 Shallow Preference Signals: Large Language Model Aligns Even Better with Truncated Data? ACL 2025 Smoothed Preference Optimization via ReNoise Inversion for Aligning Diffusion Models with Varied Human Preferences ICML 2025 Speculative Reward Model Boosts Decision Making Ability of LLMs Cost-Effectively ACL 2025 STAIR: Improving Safety Alignment with Introspective Reasoning ICML 2025 STaR-SQL: Self-Taught Reasoner for Text-to-SQL ACL 2025 Structural Reward Model: Enhancing Interpretability, Efficiency, and Scalability in Reward Modeling EMNLP 2025 Symmetric Reinforcement Learning Loss for Robust Learning on Diverse Tasks and Model Scales ICML 2025 T2V-Turbo-v2: Enhancing Video Model Post-Training through Data, Reward, and Conditional Guidance Design ICLR 2025 Taming Overconfidence in LLMs: Reward Calibration in RLHF ICLR 2025