preference learning

Rethinking Reward Modeling in Preference-based Large Language Model Alignment ICLR 2025 Reversal of Thought: Enhancing Large Language Models with Preference-Guided Reverse Reasoning Warm-up ACL 2025 Reward Generalization in RLHF: A Topological Perspective ACL 2025 Reward Model Perspectives: Whose Opinions Do Reward Models Reward? EMNLP 2025 RLAIF-V: Open-Source AI Feedback Leads to Super GPT-4V Trustworthiness CVPR 2025 RocketEval: Efficient automated LLM evaluation via grading checklist ICLR 2025 RouteLLM: Learning to Route LLMs from Preference Data ICLR 2025 RRM: Robust Reward Model Training Mitigates Reward Hacking ICLR 2025 SaMer: A Scenario-aware Multi-dimensional Evaluator for Large Language Models ICLR 2025 SELF-EVOLVED REWARD LEARNING FOR LLMS ICLR 2025 Self-Training Meets Consistency: Improving LLMs’ Reasoning with Consistency-Driven Rationale Evaluation NAACL 2025 SH at WMT25 General Machine Translation Task EMNLP 2025 Sightation Counts: Leveraging Sighted User Feedback in Building a BLV-aligned Dataset of Diagram Descriptions ACL 2025 SIMPLEMIX: Frustratingly Simple Mixing of Off- and On-policy Data in Language Model Preference Learning ICML 2025 SimulPL: Aligning Human Preferences in Simultaneous Machine Translation ICLR 2025 Sources of Disagreement in Data for LLM Instruction Tuning COLING 2025 SPaR: Self-Play with Tree-Search Refinement to Improve Instruction-Following in Large Language Models ICLR 2025 Spatial Layouts in News Homepages Capture Human Preferences EMNLP 2025 Spread Preference Annotation: Direct Preference Judgment for Efficient LLM Alignment ICLR 2025 STeCa: Step-level Trajectory Calibration for LLM Agent Learning ACL 2025 Stop Learning it all to Mitigate Visual Hallucination, Focus on the Hallucination Target. CVPR 2025 Subtle Errors in Reasoning: Preference Learning via Error-injected Self-editing ACL 2025 SYNAPSE: SYmbolic Neural-Aided Preference Synthesis Engine AAAI 2025 SynthesizeMe! Inducing Persona-Guided Prompts for Personalized Reward Models in LLMs ACL 2025 T2A-Feedback: Improving Basic Capabilities of Text-to-Audio Generation via Fine-grained AI Feedback ACL 2025