model alignment

Command R7B Arabic: a small, enterprise-focused, multilingual, and culturally aware Arabic LLM ACL 2025 Comparing Bad Apples to Good Oranges Aligning Large Language Models via Joint Preference Optimization ACL 2025 Confusion is the Final Barrier: Rethinking Jailbreak Evaluation and Investigating the Real Misuse Threat of LLMs EMNLP 2025 Correcting Large Language Model Behavior via Influence Function AAAI 2025 Correcting Negative Bias in Large Language Models through Negative Attention Score Alignment NAACL 2025 COVER: Context-Driven Over-Refusal Verification in LLMs ACL 2025 Data to Defense: The Role of Curation in Aligning Large Language Models Against Safety Compromise EMNLP 2025 DavIR: Data Selection via Implicit Reward for Large Language Models ACL 2025 Debate Helps Weak-to-Strong Generalization AAAI 2025 Diff2Flow: Training Flow Matching Models via Diffusion Model Alignment CVPR 2025 Does Refusal Training in LLMs Generalize to the Past Tense? ICLR 2025 Do LLMs Behave as Claimed? Investigating How LLMs Follow Their Own Claims using Counterfactual Questions EMNLP 2025 DyMO: Training-Free Diffusion Model Alignment with Dynamic Multi-Objective Scheduling CVPR 2025 Dynamic Steering With Episodic Memory For Large Language Models ACL 2025 ELAB: Extensive LLM Alignment Benchmark in Persian Language ACL 2025 Enhancing Large Vision-Language Models with Ultra-Detailed Image Caption Generation EMNLP 2025 Enhancing Machine Translation with Self-Supervised Preference Data ACL 2025 Evaluating Model Alignment with Human Perception: A Study on Shitsukan in LLMs and LVLMs COLING 2025 Federated Oriented Learning: A Practical One-Shot Personalized Federated Learning Framework ICML 2025 Fine-Tuning Lowers Safety and Disrupts Evaluation Consistency ACL 2025 FocalPO: Enhancing Preference Optimizing by Focusing on Correct Preference Rankings ACL 2025 Focused-DPO: Enhancing Code Generation Through Focused Preference Optimization on Error-Prone Points ACL 2025 From Distributional to Overton Pluralism: Investigating Large Language Model Alignment NAACL 2025 From Lists to Emojis: How Format Bias Affects Model Alignment ACL 2025 Governance in Motion: Co-evolution of Constitutions and AI models for Scalable Safety EMNLP 2025