Reinforcement Learning from Human Feedback

A Systematic Analysis of Base Model Choice for Reward Modeling EMNLP 2025 Bayesian WeakS-to-Strong from Text Classification to Generation ICLR 2025 Better Instruction-Following Through Minimum Bayes Risk ICLR 2025 Beyond Online Sampling: Bridging Offline-to-Online Alignment via Dynamic Data Transformation for LLMs EMNLP 2025 Binary Classifier Optimization for Large Language Model Alignment ACL 2025 CareBot: A Pioneering Full-Process Open-Source Medical Language Model AAAI 2025 CARMO: Dynamic Criteria Generation for Context Aware Reward Modelling ACL 2025 Comparing Bad Apples to Good Oranges Aligning Large Language Models via Joint Preference Optimization ACL 2025 Continual SFT Matches Multimodal RLHF with Negative Supervision CVPR 2025 Data with High and Consistent Preference Difference Are Better for Reward Model AAAI 2025 Debate Helps Weak-to-Strong Generalization AAAI 2025 Differentiable Reward Optimization for LLM based TTS system Interspeech 2025 DiffPO: Diffusion-styled Preference Optimization for Inference Time Alignment of Large Language Models ACL 2025 Enhancing Large Vision-Language Models with Ultra-Detailed Image Caption Generation EMNLP 2025 Expectation Confirmation Preference Optimization for Multi-Turn Conversational Recommendation Agent ACL 2025 Expectation Preference Optimization: Reliable Preference Estimation for Improving the Reasoning Capability of Large Language Models EMNLP 2025 Fine-Tuning Text-to-Speech Diffusion Models Using Reinforcement Learning with Human Feedback Interspeech 2025 FloorPlan-LLaMa: Aligning Architects’ Feedback and Domain Knowledge in Architectural Floor Plan Generation ACL 2025 FocalPO: Enhancing Preference Optimizing by Focusing on Correct Preference Rankings ACL 2025 FRACTAL: Fine-Grained Scoring from Aggregate Text Labels ACL 2025 From Lists to Emojis: How Format Bias Affects Model Alignment ACL 2025 GenderAlign: An Alignment Dataset for Mitigating Gender Bias in Large Language Models ACL 2025 HAF-RM: A Hybrid Alignment Framework for Reward Model Training ACL 2025 Intuitive Fine-Tuning: Towards Simplifying Alignment into a Single Process ACL 2025 IPO: Your Language Model is Secretly a Preference Classifier ACL 2025