llm alignment

LLM Alignment as Retriever Optimization: An Information Retrieval Perspective ICML 2025 Massive Supervised Fine-tuning Experiments Reveal How Data, Layer, and Training Factors Shape LLM Alignment Quality EMNLP 2025 Meta-Rewarding Language Models: Self-Improving Alignment with LLM-as-a-Meta-Judge EMNLP 2025 Multi-Domain Explainability of Preferences EMNLP 2025 Multi-lingual Multi-turn Automated Red Teaming for LLMs NAACL 2025 QA‐LIGN: Aligning LLMs through Constitutionally Decomposed QA EMNLP 2025 RED: Unleashing Token-Level Rewards from Holistic Feedback via Reward Redistribution EMNLP 2025 Reinforcement Learning for Large Language Models via Group Preference Reward Shaping EMNLP 2025 RMB: Comprehensively benchmarking reward models in LLM alignment ICLR 2025 SATA: A Paradigm for LLM Jailbreak via Simple Assistive Task Linkage ACL 2025 Self-Boosting Large Language Models with Synthetic Preference Data ICLR 2025 Token-Aware Editing of Internal Activations for Large Language Model Alignment EMNLP 2025 Toward Optimal LLM Alignments Using Two-Player Games EMNLP 2025 UAlign: LLM Alignment Benchmark for the Ukrainian Language ACL 2025 ZEBRA: Leveraging Model-Behavioral Knowledge for Zero-Annotation Preference Dataset Construction EMNLP 2025 Advancing Adversarial Suffix Transfer Learning on Aligned Large Language Models EMNLP 2024 A Grounded Preference Model for LLM Alignment ACL 2024 Distract Large Language Models for Automatic Jailbreak Attack EMNLP 2024 DogeRM: Equipping Reward Models with Domain Knowledge through Model Merging EMNLP 2024 Getting More Juice Out of the SFT Data: Reward Learning from Human Demonstration Improves SFT for LLM Alignment NeurIPS 2024 KorNAT: LLM Alignment Benchmark for Korean Social Values and Common Knowledge ACL 2024 Reasons to Reject? Aligning Language Models with Judgments ACL 2024 Self-Evolution Fine-Tuning for Policy Optimization EMNLP 2024 SimPO: Simple Preference Optimization with a Reference-Free Reward NeurIPS 2024 Stress-Testing Capability Elicitation With Password-Locked Models NeurIPS 2024