← Keywords

preference learning

411 papers

Explore in graph

Also known as

DPO PL

Co-occurring keywords

large language model (12755) reinforcement learning (4122) direct preference optimization (317) reinforcement learning from human feedback (261) language model alignment (142) reward model (251) human feedback (161) reward modeling (159) model alignment (219) human preference (120)

Papers

Multi-Reference Preference Optimization for Large Language Models AAAI 2025
Aligning to Constraints for Data-Efficient Language Model Customization NAACL 2025
Beyond Under-Alignment: Atomic Preference Enhanced Factuality Tuning for Large Language Models NAACL 2025
Aligning to What? Limits to RLHF Based Alignment NAACL 2025
Understanding Reference Policies in Direct Preference Optimization NAACL 2025
2D-DPO: Scaling Direct Preference Optimization with 2-Dimensional Supervision NAACL 2025
Evaluating Design Choices in Verifiable Generation with Open-source Models NAACL 2025
MWPO: Enhancing LLMs Performance through Multi-Weight Preference Strength and Length Optimization ACL 2025
Mitigating Object Hallucinations via Sentence-Level Early Intervention ICCV 2025
Token-Level Accept or Reject: A Micro Alignment Approach for Large Language Models IJCAI 2025
Verifiable by Design: Aligning Language Models to Quote from Pre-Training Data NAACL 2025
Indirect Online Preference Optimization via Reinforcement Learning IJCAI 2025
Debiasing Online Preference Learning via Preference Feature Preservation ACL 2025
Subtle Errors in Reasoning: Preference Learning via Error-injected Self-editing ACL 2025
Towards Uncertainty Unification: A Case Study for Preference Learning RSS 2025
PopAlign: Diversifying Contrasting Patterns for a More Comprehensive Alignment ACL 2025
MPO: Multilingual Safety Alignment via Reward Gap Optimization ACL 2025
Hybrid Preferences: Learning to Route Instances for Human vs. AI Feedback ACL 2025
High-Dimension Human Value Representation in Large Language Models NAACL 2025
Agentic Reward Modeling: Integrating Human Preferences with Verifiable Correctness Signals for Reliable Reward Systems ACL 2025
GenderAlign: An Alignment Dataset for Mitigating Gender Bias in Large Language Models ACL 2025
MVReward: Better Aligning and Evaluating Multi-View Diffusion Models with Human Preferences AAAI 2025
Stop Learning it all to Mitigate Visual Hallucination, Focus on the Hallucination Target. CVPR 2025
SynthesizeMe! Inducing Persona-Guided Prompts for Personalized Reward Models in LLMs ACL 2025
LLaVA-Critic: Learning to Evaluate Multimodal Models CVPR 2025