{"total":42,"rows":[{"id":"2309.15025","title":"Large Language Model Alignment: A Survey","created":"2023-09-26","cited_by_count":243,"area":"alignment"},{"id":"2502.17420","title":"The Geometry of Refusal in Large Language Models: Concept Cones and Representational Independence","created":"2025-02-24","cited_by_count":115,"area":"alignment"},{"id":"2406.05644","title":"How Alignment and Jailbreak Work: Explain LLM Safety through Intermediate Hidden States","created":"2024-06-09","cited_by_count":98,"area":"alignment"},{"id":"2409.18169","title":"Harmful Fine-tuning Attacks and Defenses for Large Language Models: A Survey","created":"2024-09-26","cited_by_count":90,"area":"alignment"},{"id":"2402.09267","title":"Self-Alignment for Factuality: Mitigating Hallucinations in LLMs via Self-Evaluation","created":"2024-02-14","cited_by_count":80,"area":"alignment"},{"id":"2312.07000","title":"Alignment for Honesty","created":"2023-12-12","cited_by_count":74,"area":"alignment"},{"id":"2311.18743","title":"AlignBench: Benchmarking Chinese Alignment of Large Language Models","created":"2023-11-30","cited_by_count":68,"area":"alignment"},{"id":"2405.10301","title":"Conformal Alignment: Knowing When to Trust Foundation Models with Guarantees","created":"2024-05-16","cited_by_count":54,"area":"alignment"},{"id":"2412.15280","title":"Context-DPO: Aligning Language Models for Context-Faithfulness","created":"2024-12-18","cited_by_count":50,"area":"alignment"},{"id":"2503.11701","title":"A Survey of Direct Preference Optimization","created":"2025-03-12","cited_by_count":36,"area":"alignment"},{"id":"2309.11166","title":"Are Large Language Models Really Robust to Word-Level Perturbations?","created":"2023-09-20","cited_by_count":32,"area":"alignment"},{"id":"2404.11049","title":"Stepwise Alignment for Constrained Language Model Policy Optimization","created":"2024-04-17","cited_by_count":30,"area":"alignment"},{"id":"2503.18991","title":"Inverse Reinforcement Learning with Dynamic Reward Scaling for LLM Alignment","created":"2025-03-23","cited_by_count":20,"area":"alignment"},{"id":"2506.05346","title":"Why LLM Safety Guardrails Collapse After Fine-tuning: A Similarity Analysis Between Alignment and Fine-tuning Datasets","created":"2025-06-05","cited_by_count":20,"area":"alignment"},{"id":"2502.13775","title":"VITAL: A New Dataset for Benchmarking Pluralistic Alignment in Healthcare","created":"2025-02-19","cited_by_count":17,"area":"alignment"},{"id":"2507.14987","title":"AlphaAlign: Incentivizing Safety Alignment with Extremely Simplified Reinforcement Learning","created":"2025-07-20","cited_by_count":15,"area":"alignment"},{"id":"2507.19672","title":"Alignment and Safety in Large Language Models: Safety Mechanisms, Training Paradigms, and Emerging Challenges","created":"2025-07-25","cited_by_count":15,"area":"alignment"},{"id":"2407.16637","title":"Course-Correction: Safety Alignment Using Synthetic Preferences","created":"2024-07-23","cited_by_count":13,"area":"alignment"},{"id":"2403.18341","title":"IterAlign: Iterative Constitutional Alignment of Large Language Models","created":"2024-03-27","cited_by_count":11,"area":"alignment"},{"id":"2406.18346","title":"AI Alignment through Reinforcement Learning from Human Feedback? Contradictions and Limitations","created":"2024-06-26","cited_by_count":11,"area":"alignment"},{"id":"2507.03662","title":"Re-Emergent Misalignment: How Narrow Fine-Tuning Erodes Safety Alignment in LLMs","created":"2025-07-04","cited_by_count":9,"area":"alignment"},{"id":"2511.14476","title":"Operationalizing Pluralistic Values in Large Language Model Alignment Reveals Trade-offs in Safety, Inclusivity, and Model Behavior","created":"2025-11-18","cited_by_count":9,"area":"alignment"},{"id":"2604.19018","title":"Local Linearity of LLMs Enables Activation Steering via Model-Based Linear Optimal Control","created":"2026-04-21","cited_by_count":9,"area":"alignment"},{"id":"2503.00069","title":"Societal Alignment Frameworks Can Improve LLM Alignment","created":"2025-02-27","cited_by_count":8,"area":"alignment"},{"id":"2504.12911","title":"Benchmarking Multi-National Value Alignment for Large Language Models","created":"2025-04-17","cited_by_count":7,"area":"alignment"},{"id":"2410.12491","title":"Insights from the Inverse: Reconstructing LLM Training Goals Through Inverse Reinforcement Learning","created":"2024-10-16","cited_by_count":6,"area":"alignment"},{"id":"2403.14683","title":"A Moral Imperative: The Need for Continual Superalignment of Large Language Models","created":"2024-03-13","cited_by_count":5,"area":"alignment"},{"id":"2504.16628","title":"ParetoHqD: Fast Offline Multiobjective Alignment of Large Language Models using Pareto High-quality Data","created":"2025-04-23","cited_by_count":4,"area":"alignment"},{"id":"2506.07523","title":"Aligning What LLMs Do and Say: Towards Self-Consistent Explanations","created":"2025-06-09","cited_by_count":4,"area":"alignment"},{"id":"2510.13512","title":"Offline and Online KL-Regularized RLHF under Differential Privacy","created":"2025-10-15","cited_by_count":4,"area":"alignment"},{"id":"2406.01931","title":"Dishonesty in Helpful and Harmless Alignment","created":"2024-06-04","cited_by_count":3,"area":"alignment"},{"id":"2502.02153","title":"Vulnerability Mitigation for Safety-Aligned Language Models via Debiasing","created":"2025-02-04","cited_by_count":3,"area":"alignment"},{"id":"2504.12553","title":"ELAB: Extensive LLM Alignment Benchmark in Persian Language","created":"2025-04-17","cited_by_count":2,"area":"alignment"},{"id":"2606.19744","title":"Beyond Uniform Forgetting: A Study of Sequential Direct Preference Optimization Across Preference Settings","created":"2026-06-18","cited_by_count":1,"area":"alignment"},{"id":"2505.01706","title":"Inducing Robustness in a 2 Dimensional Direct Preference Optimization Paradigm","created":"2025-05-03","cited_by_count":0,"area":"alignment"},{"id":"2602.04294","title":"How Few-shot Demonstrations Affect Prompt-based Defenses Against LLM Jailbreak Attacks","created":"2026-02-04","cited_by_count":0,"area":"alignment"},{"id":"2604.07754","title":"The Art of (Mis)alignment: How Fine-Tuning Methods Effectively Misalign and Realign LLMs in Post-Training","created":"2026-04-09","cited_by_count":0,"area":"alignment"},{"id":"2604.24429","title":"A Multi-Dimensional Audit of Politically Aligned Large Language Models","created":"2026-04-27","cited_by_count":0,"area":"alignment"},{"id":"2608.24192","title":"Preference Data Selection for Mitigating the Alignment Tax in Large Language Models","created":"2026-08-25","cited_by_count":0,"area":"alignment"},{"id":"2609.32189","title":"ScopeIF: Improving Scope-Aware Precise Instruction-Following in Large Language Models via Graded Reward Modeling","created":"2026-09-26","cited_by_count":0,"area":"alignment"},{"id":"2609.32717","title":"LLM Alignment--Utility Asymmetry under Semantic-Preserving Transformations","created":"2026-09-26","cited_by_count":0,"area":"alignment"},{"id":"2610.09600","title":"SafeEvo: Deciphering the Safety Alignment Mechanism and Evolution in Language Models","created":"2026-10-07","cited_by_count":0,"area":"alignment"}],"next_cursor":null}