Skip to content
conftrace_

direct preference optimization

427 papers

Explore in graph

Also known as

DPO

Co-occurring keywords · papers mentioning both

large language model (156) reinforcement learning from human feedback (63) preference optimization (50) preference learning (46) language model alignment (45) supervised fine-tuning (44) preference alignment (37) reward model (33) reinforcement learning (32) model alignment (32)

Papers

Rethinking DPO: The Role of Rejected Responses in Preference Misalignment EMNLP 2025 Retrieval-Augmented Fine-Tuning With Preference Optimization For Visual Program Generation ACL 2025 Reverse Preference Optimization for Complex Instruction Following ACL 2025 Reward-Augmented Data Enhances Direct Preference Alignment of LLMs ICML 2025 RLHF Algorithms Ranked: An Extensive Evaluation Across Diverse Tasks, Rewards, and Hyperparameters EMNLP 2025 Robust Multi-Objective Preference Alignment with Online DPO AAAI 2025 Robust Preference Optimization via Dynamic Target Margins ACL 2025 RRM: Robust Reward Model Training Mitigates Reward Hacking ICLR 2025 Scalable Ranked Preference Optimization for Text-to-Image Generation ICCV 2025 sDPO: Don’t Use Your Data All at Once COLING 2025 SDPO: Segment-Level Direct Preference Optimization for Social Agents ACL 2025 Selective Preference Optimization via Token-Level Reward Function Estimation EMNLP 2025 Self-Correction is More than Refinement: A Learning Framework for Visual and Language Reasoning Tasks ACL 2025 Self-Improvement Towards Pareto Optimality: Mitigating Preference Conflicts in Multi-Objective Alignment ACL 2025 SeRA: Self-Reviewing and Alignment of LLMs using Implicit Reward Margins ICLR 2025 SGDPO: Self-Guided Direct Preference Optimization for Language Model Alignment ACL 2025 Shallow Preference Signals: Large Language Model Aligns Even Better with Truncated Data? ACL 2025 SILMM: Self-Improving Large Multimodal Models for Compositional Text-to-Image Generation CVPR 2025 SMART: Simulated Students Aligned with Item Response Theory for Question Difficulty Prediction EMNLP 2025 SparsePO: Controlling Preference Alignment of LLMs via Sparse Token Masks EMNLP 2025 SPO: Self Preference Optimization with Self Regularization EMNLP 2025 Step-by-Step Mastery: Enhancing Soft Constraint Following Ability of Large Language Models ACL 2025 Stress-testing Machine Generated Text Detection: Shifting Language Models Writing Style to Fool Detectors ACL 2025 Subtle Errors in Reasoning: Preference Learning via Error-injected Self-editing ACL 2025 SuperCorrect: Advancing Small LLM Reasoning with Thought Template Distillation and Self-Correction ICLR 2025