model alignment

Rethinking DPO-style Diffusion Aligning Frameworks ICCV 2025 Rethinking what matters: Effective and Robust Multilingual Realignment for Low-Resource Languages IJCNLP 2025 Reverse Preference Optimization for Complex Instruction Following ACL 2025 Reward Model Perspectives: Whose Opinions Do Reward Models Reward? EMNLP 2025 Robust Preference Optimization via Dynamic Target Margins ACL 2025 SafeLawBench: Towards Safe Alignment of Large Language Models ACL 2025 Scalable Extraction of Training Data from Aligned, Production Language Models ICLR 2025 SCANS: Mitigating the Exaggerated Safety for LLMs via Safety-Conscious Activation Steering AAAI 2025 SeaPO: Strategic Error Amplification for Robust Preference Optimization of Large Language Models EMNLP 2025 Self-Augmented Preference Alignment for Sycophancy Reduction in LLMs EMNLP 2025 Self-Evolutionary Large Language Models Through Uncertainty-Enhanced Preference Optimization AAAI 2025 SELF-EVOLVED REWARD LEARNING FOR LLMS ICLR 2025 Semantics-Adaptive Activation Intervention for LLMs via Dynamic Steering Vectors ICLR 2025 ShortFT: Diffusion Model Alignment via Shortcut-based Fine-Tuning ICCV 2025 Single Character Perturbations Break LLM Alignment AAAI 2025 Soteria: Language-Specific Functional Parameter Steering for Multilingual Safety Alignment EMNLP 2025 SPICA: Retrieving Scenarios for Pluralistic In-Context Alignment ACL 2025 sudoLLM: On Multi-role Alignment of Language Models EMNLP 2025 Test-time Alignment of Diffusion Models without Reward Over-optimization ICLR 2025 Token-Aware Editing of Internal Activations for Large Language Model Alignment EMNLP 2025 Token-Level Accept or Reject: A Micro Alignment Approach for Large Language Models IJCAI 2025 Tongue-Tied: Breaking LLMs Safety Through New Language Learning NAACL 2025 Too Helpful, Too Harmless, Too Honest or Just Right? EMNLP 2025 Toward Guidance-Free AR Visual Generation via Condition Contrastive Alignment ICLR 2025 Toward Optimal LLM Alignments Using Two-Player Games EMNLP 2025