{"total":31,"rows":[{"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":"2506.07468","title":"Chasing Moving Targets with Online Self-Play Reinforcement Learning for Safer Language Models","created":"2025-06-09","cited_by_count":39,"area":"alignment"},{"id":"2410.03523","title":"A Probabilistic Perspective on Unlearning and Alignment for Large Language Models","created":"2024-10-04","cited_by_count":21,"area":"alignment"},{"id":"2503.02574","title":"LLM-Safety Evaluations Lack Robustness","created":"2025-03-04","cited_by_count":18,"area":"alignment"},{"id":"2505.20259","title":"Lifelong Safety Alignment for Language Models","created":"2025-05-26","cited_by_count":15,"area":"alignment"},{"id":"2502.11455","title":"Adversary-Aware DPO: Enhancing Safety Alignment in Vision Language Models via Adversarial Training","created":"2025-02-17","cited_by_count":12,"area":"alignment"},{"id":"2509.15202","title":"Beyond Surface Alignment: Rebuilding LLMs Safety Mechanism via Probabilistically Ablating Refusal Direction","created":"2025-09-18","cited_by_count":8,"area":"alignment"},{"id":"2512.20806","title":"Safety Alignment of LMs via Non-cooperative Games","created":"2025-12-23","cited_by_count":8,"area":"alignment"},{"id":"2501.10639","title":"Latent-space adversarial training with post-aware calibration for defending large language models against jailbreak attacks","created":"2025-01-18","cited_by_count":7,"area":"alignment"},{"id":"2505.24369","title":"Adversarial Preference Learning for Robust LLM Alignment","created":"2025-05-30","cited_by_count":7,"area":"alignment"},{"id":"2605.02946","title":"RouteHijack: Routing-Aware Attack on Mixture-of-Experts LLMs","created":"2026-05-01","cited_by_count":6,"area":"alignment"},{"id":"2410.00451","title":"Unleashing the Unseen: Harnessing Benign Datasets for Jailbreaking Large Language Models","created":"2024-10-01","cited_by_count":4,"area":"alignment"},{"id":"2506.16078","title":"Probing the Robustness of Large Language Models Safety to Latent Perturbations","created":"2025-06-19","cited_by_count":4,"area":"alignment"},{"id":"2511.19218","title":"Adversarial Attack-Defense Co-Evolution for LLM Safety Alignment via Tree-Group Dual-Aware Search and Optimization","created":"2025-11-24","cited_by_count":4,"area":"alignment"},{"id":"2603.07445","title":"Few Tokens, Big Leverage: Preserving Safety Alignment by Constraining Safety Tokens during Fine-tuning","created":"2026-03-08","cited_by_count":4,"area":"alignment"},{"id":"2510.18081","title":"Any-Depth Alignment: Unlocking Innate Safety Alignment of LLMs to Any-Depth","created":"2025-10-20","cited_by_count":3,"area":"alignment"},{"id":"2601.07200","title":"Safeguarding LLM Fine-tuning via Push-Pull Distributional Alignment","created":"2026-01-12","cited_by_count":2,"area":"alignment"},{"id":"2602.16977","title":"Fail-Closed Alignment for Large Language Models","created":"2026-02-19","cited_by_count":2,"area":"alignment"},{"id":"2602.23391","title":"Detoxifying LLMs via Representation Erasure-Based Preference Optimization","created":"2026-02-24","cited_by_count":1,"area":"alignment"},{"id":"2607.07918","title":"Efficient Safety Alignment of Language Models via Latent Personality Traits","created":"2026-07-08","cited_by_count":1,"area":"alignment"},{"id":"2605.28030","title":"SPARD: Defending Harmful Fine-Tuning Attack via Safety Projection with Relevance-Diversity Data Selection","created":"2026-05-27","cited_by_count":0,"area":"alignment"},{"id":"2606.04168","title":"When Autoregressive Consistency Hurts Safety Alignment","created":"2026-06-02","cited_by_count":0,"area":"alignment"},{"id":"2606.04778","title":"Inference-Time Vulnerability Beyond Shallow Safety: Alignment Along Generation Trajectories","created":"2026-06-03","cited_by_count":0,"area":"alignment"},{"id":"2606.04929","title":"Sequential Data Poisoning in LLM Post-Training","created":"2026-06-03","cited_by_count":0,"area":"alignment"},{"id":"2606.16349","title":"From Refusal Geometry to Safety Geometry: Harmfulness--Refusal Coupling under Dynamic Adversarial Fine-Tuning","created":"2026-06-15","cited_by_count":0,"area":"alignment"},{"id":"2607.00572","title":"HARC: Coupling Harmfulness and Refusal Directions for Robust Safety Alignment","created":"2026-07-01","cited_by_count":0,"area":"alignment"},{"id":"2607.19371","title":"Mitigating Scaffolding Collapse in Socratic Tutors via Representation Alignment","created":"2026-06-15","cited_by_count":0,"area":"alignment"},{"id":"2608.01414","title":"No Single Neuron of Failure: Distributed Safety Alignment Against White-Box Attacks","created":"2026-08-02","cited_by_count":0,"area":"alignment"},{"id":"2608.02674","title":"Moving the Safety Barrier: Dynamic Routing Adaptive Alignment Against White-Box Attacks","created":"2026-08-02","cited_by_count":0,"area":"alignment"},{"id":"2608.26222","title":"NeuronFuzz: Safety Neuron Guided Fuzzing for LLM Safety Evaluation","created":"2026-08-26","cited_by_count":0,"area":"alignment"},{"id":"2609.06934","title":"The Geometry of Refusal: Why Post-Hoc Safety Is Fragile and Pretraining-Time Safety Persists","created":"2026-09-07","cited_by_count":0,"area":"alignment"}],"next_cursor":null}