Reinforcement Learning from Human Feedback

Improving Neutral Point-of-View Generation with Data- and Parameter-Efficient RL EMNLP 2025 InvestAlign: Overcoming Data Scarcity in Aligning Large Language Models with Investor Decision-Making Processes Under Herd Behavior ACL 2025 IOPO: Empowering LLMs with Complex Instruction Following via Input-Output Preference Optimization ACL 2025 Joint Reward and Policy Learning with Demonstrations and Human Feedback Improves Alignment ICLR 2025 KazBench-KK: A Cultural-Knowledge Benchmark for Kazakh ACL 2025 Learning from Imperfect Human Feedback: A Tale from Corruption-Robust Dueling ICLR 2025 Learning Together to Perform Better: Teaching Small-Scale LLMs to Collaborate via Preferential Rationale Tuning ACL 2025 LEGEND: Leveraging Representation Engineering to Annotate Safety Margin for Preference Datasets AAAI 2025 Logical Reasoning with Outcome Reward Models for Test-Time Scaling EMNLP 2025 LookAlike: Consistent Distractor Generation in Math MCQs ACL 2025 Lost in the Context: Insufficient and Distracted Attention to Contexts in Preference Modeling ACL 2025 Model Extrapolation Expedites Alignment ACL 2025 Multi-Player Approaches for Dueling Bandits AISTATS 2025 Mutual-Taught for Co-adapting Policy and Reward Models ACL 2025 MVReward: Better Aligning and Evaluating Multi-View Diffusion Models with Human Preferences AAAI 2025 OmniAlign-V: Towards Enhanced Alignment of MLLMs with Human Preference ACL 2025 On-the-fly Preference Alignment via Principle-Guided Decoding ICLR 2025 OpenRLHF: A Ray-based Easy-to-use, Scalable and High-performance RLHF Framework EMNLP 2025 Permutative Preference Alignment from Listwise Ranking of Human Judgments EMNLP 2025 PLLuM-Align: Polish Preference Dataset for Large Language Model Alignment EMNLP 2025 Policy Teaching via Data Poisoning in Learning from Human Preferences AISTATS 2025 PopAlign: Diversifying Contrasting Patterns for a More Comprehensive Alignment ACL 2025 Preference Optimization for Reasoning with Pseudo Feedback ICLR 2025 Reinforcement Learning from Imperfect Corrective Actions and Proxy Rewards ICLR 2025 Reinforcement Learning from Multi-level and Episodic Human Feedback L4DC 2025