{"total":96,"rows":[{"id":"2406.05946","title":"Safety Alignment Should Be Made More Than Just a Few Tokens Deep","created":"2024-06-10","cited_by_count":472,"area":"alignment"},{"id":"2408.17003","title":"Safety Layers in Aligned Large Language Models: The Key to LLM Security","created":"2024-08-30","cited_by_count":134,"area":"alignment"},{"id":"2402.01109","title":"Vaccine: Perturbation-aware Alignment for Large Language Models against Harmful Fine-tuning Attack","created":"2024-02-02","cited_by_count":115,"area":"alignment"},{"id":"2402.18540","title":"Keeping LLMs Aligned After Fine-tuning: The Crucial Role of Prompt Templates","created":"2024-02-28","cited_by_count":96,"area":null},{"id":"2405.14577","title":"Representation Noising: A Defence Mechanism Against Harmful Finetuning","created":"2024-05-23","cited_by_count":96,"area":"safety"},{"id":"2409.01586","title":"Booster: Tackling Harmful Fine-tuning for Large Language Models via Attenuating Harmful Perturbation","created":"2024-09-03","cited_by_count":92,"area":null},{"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":"2408.09600","title":"Antidote: Post-fine-tuning Safety Alignment for Large Language Models against Harmful Fine-tuning","created":"2024-08-18","cited_by_count":72,"area":"alignment"},{"id":"2410.07471","title":"SEAL: Safety-enhanced Aligned LLM Fine-tuning via Bilevel Data Selection","created":"2024-10-09","cited_by_count":64,"area":null},{"id":"2310.19698","title":"When Do Prompting and Prefix-Tuning Work? A Theory of Capabilities and Limitations","created":"2023-10-30","cited_by_count":43,"area":null},{"id":"2505.14646","title":"CAD-Coder: An Open-Source Vision-Language Model for Computer-Aided Design Code Generation","created":"2025-05-20","cited_by_count":43,"area":null},{"id":"2501.01765","title":"SaLoRA: Safety-Alignment Preserved Low-Rank Adaptation","created":"2025-01-03","cited_by_count":42,"area":"safety"},{"id":"2410.09760","title":"Targeted Vaccine: Safety Alignment for Large Language Models against Harmful Fine-Tuning via Layer-wise Perturbation","created":"2024-10-13","cited_by_count":37,"area":"alignment"},{"id":"2503.17239","title":"SafeMERGE: Preserving Safety Alignment in Fine-Tuned Large Language Models via Selective Layer-Wise Model Merging","created":"2025-03-21","cited_by_count":25,"area":"alignment"},{"id":"2409.16223","title":"Fine-Tuning is Fine, if Calibrated","created":"2024-09-24","cited_by_count":24,"area":null},{"id":"2408.14471","title":"A Practitioner's Guide to Continual Multimodal Pretraining","created":"2024-08-26","cited_by_count":23,"area":null},{"id":"2505.06843","title":"Benign Samples Matter! Fine-tuning On Outlier Benign Samples Severely Breaks Safety","created":"2025-05-11","cited_by_count":22,"area":"safety"},{"id":"2404.09447","title":"kNN-CLIP: Retrieval Enables Training-Free Segmentation on Continually Expanding Large Vocabularies","created":"2024-04-15","cited_by_count":20,"area":null},{"id":"2501.18100","title":"Panacea: Mitigating Harmful Fine-tuning for Large Language Models via Post-fine-tuning Perturbation","created":"2025-01-30","cited_by_count":20,"area":null},{"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":"2506.08473","title":"AsFT: Anchoring Safety During LLM Fine-Tuning Within Narrow Safety Basin","created":"2025-06-10","cited_by_count":19,"area":null},{"id":"2411.04420","title":"BendVLM: Test-Time Debiasing of Vision-Language Embeddings","created":"2024-11-07","cited_by_count":17,"area":"mllm"},{"id":"2502.08301","title":"Compromising Honesty and Harmlessness in Language Models via Deception Attacks","created":"2025-02-12","cited_by_count":17,"area":null},{"id":"2506.03850","title":"Vulnerability-Aware Alignment: Mitigating Uneven Forgetting in Harmful Fine-Tuning","created":"2025-06-04","cited_by_count":17,"area":"alignment"},{"id":"2508.06249","title":"In-Training Defenses against Emergent Misalignment in Language Models","created":"2025-08-08","cited_by_count":15,"area":"alignment"},{"id":"2506.14087","title":"Multi-Scale Finetuning for Encoder-based Time Series Foundation Models","created":"2025-06-17","cited_by_count":14,"area":null},{"id":"2505.17646","title":"Unveiling the Basin-Like Loss Landscape in Large Language Models","created":"2025-05-23","cited_by_count":13,"area":null},{"id":"2506.07891","title":"Video Unlearning via Low-Rank Refusal Vector","created":"2025-06-09","cited_by_count":13,"area":"safety"},{"id":"2310.15105","title":"FD-Align: Feature Discrimination Alignment for Fine-tuning Pre-Trained Models in Few-Shot Learning","created":"2023-10-23","cited_by_count":12,"area":null},{"id":"2503.06881","title":"ResMoE: Space-efficient Compression of Mixture of Experts LLMs via Residual Restoration","created":"2025-03-10","cited_by_count":12,"area":"moe"},{"id":"2506.15606","title":"LoX: Low-Rank Extrapolation Robustifies LLM Safety Against Fine-tuning","created":"2025-06-18","cited_by_count":12,"area":"safety"},{"id":"2510.27172","title":"Adaptive Defense against Harmful Fine-Tuning for Large Language Models via Bayesian Data Scheduler","created":"2025-10-31","cited_by_count":12,"area":null},{"id":"2505.16559","title":"CTRAP: Embedding Collapse Trap to Safeguard Large Language Models from Harmful Fine-Tuning","created":"2025-05-22","cited_by_count":11,"area":"safety"},{"id":"2505.17196","title":"Shape it Up! Restoring LLM Safety during Finetuning","created":"2025-05-22","cited_by_count":11,"area":"alignment"},{"id":"2508.07172","title":"Gradient Surgery for Safe LLM Fine-Tuning","created":"2025-08-10","cited_by_count":11,"area":"alignment"},{"id":"2505.12186","title":"Self-Destructive Language Model","created":"2025-05-18","cited_by_count":10,"area":"safety"},{"id":"2512.10150","title":"Unforgotten Safety: Preserving Safety Alignment of Large Language Models with Continual Learning","created":"2025-12-10","cited_by_count":10,"area":"alignment"},{"id":"2506.16506","title":"Subspace-Boosted Model Merging","created":"2025-06-19","cited_by_count":9,"area":null},{"id":"2510.14301","title":"A Guardrail for Safety Preservation: When Safety-Sensitive Subspace Meets Harmful-Resistant Null-Space","created":"2025-10-16","cited_by_count":9,"area":"alignment"},{"id":"2410.04524","title":"Toward Secure Tuning: Mitigating Security Risks from Instruction Fine-Tuning","created":"2024-10-06","cited_by_count":8,"area":null},{"id":"2411.01322","title":"FEET: A Framework for Evaluating Embedding Techniques","created":"2024-11-02","cited_by_count":8,"area":null},{"id":"2508.20697","title":"Token Buncher: Shielding LLMs from Harmful Reinforcement Learning Fine-Tuning","created":"2025-08-28","cited_by_count":8,"area":null},{"id":"2604.10079","title":"Why Supervised Fine-Tuning Fails to Learn: A Systematic Study of Incomplete Learning in Large Language Models","created":"2026-04-11","cited_by_count":8,"area":null},{"id":"2503.19041","title":"LookAhead Tuning: Safer Language Models via Partial Answer Previews","created":"2025-03-24","cited_by_count":7,"area":"alignment"},{"id":"2508.00264","title":"Calibrated Language Models and How to Find Them with Label Smoothing","created":"2025-08-01","cited_by_count":7,"area":null},{"id":"2502.19537","title":"No, of Course I Can! Deeper Fine-Tuning Attacks That Bypass Token-Level Safety Mechanisms","created":"2025-02-26","cited_by_count":6,"area":"safety"},{"id":"2507.17075","title":"LoRA is All You Need for Safety Alignment of Reasoning LLMs","created":"2025-07-22","cited_by_count":6,"area":"lr"},{"id":"2602.16931","title":"Narrow Fine-Tuning Erodes Safety Alignment in Vision-Language Agents","created":"2026-02-18","cited_by_count":6,"area":"mllm"},{"id":"2603.00498","title":"Antibody: Strengthening Defense Against Harmful Fine-Tuning for Large Language Models via Attenuating Harmful Gradient Influence","created":"2026-02-28","cited_by_count":6,"area":"safety"},{"id":"2607.13429","title":"Generalizable VLA Finetuning via Representation Anchoring and Language-Action Alignment","created":"2026-07-15","cited_by_count":6,"area":"mllm"},{"id":"2411.19335","title":"PEFT-as-an-Attack! Jailbreaking Language Models during Federated Parameter-Efficient Fine-Tuning","created":"2024-11-28","cited_by_count":5,"area":"safety"},{"id":"2601.08089","title":"Q-realign: Piggybacking Realignment on Quantization for Safe and Efficient LLM Deployment","created":"2026-01-13","cited_by_count":5,"area":"safety"},{"id":"2602.00722","title":"Spectral Imbalance Causes Forgetting in Low-Rank Continual Adaptation","created":"2026-01-31","cited_by_count":5,"area":null},{"id":"2602.05228","title":"Surgery: Mitigating Harmful Fine-Tuning for Large Language Models via Attention Sink","created":"2026-02-05","cited_by_count":4,"area":"alignment"},{"id":"2604.12384","title":"Preventing Safety Drift in Large Language Models via Coupled Weight and Activation Constraints","created":"2026-04-14","cited_by_count":4,"area":"alignment"},{"id":"2604.17215","title":"Continual Safety Alignment via Gradient-Based Sample Selection","created":"2026-04-19","cited_by_count":4,"area":"alignment"},{"id":"2401.10220","title":"AutoFT: Learning an Objective for Robust Fine-Tuning","created":"2024-01-18","cited_by_count":3,"area":null},{"id":"2505.11741","title":"MTRE: Multi-Token Reliability Estimation for Hallucination Detection in VLMs","created":"2025-05-16","cited_by_count":3,"area":"mllm"},{"id":"2508.16512","title":"Seeing Clearly, Forgetting Deeply: Revisiting Fine-Tuned Video Generators for Driving Simulation","created":"2025-08-22","cited_by_count":3,"area":"wm"},{"id":"2512.00021","title":"Foundation Models for Trajectory Planning in Autonomous Driving: A Review of Progress and Open Challenges","created":"2025-10-31","cited_by_count":3,"area":"driving"},{"id":"2512.01899","title":"Provably Safe Model Updates","created":"2025-12-01","cited_by_count":3,"area":null},{"id":"2505.10810","title":"MoCLIP: Motion-Aware Fine-Tuning and Distillation of CLIP for Human Motion Generation","created":"2025-05-16","cited_by_count":2,"area":null},{"id":"2506.07356","title":"Safety-Aligned Weights Are Not Enough: Refusal-Teacher-Guided Finetuning Enhances Safety and Downstream Performance under Harmful Finetuning Attacks","created":"2025-06-09","cited_by_count":2,"area":"safety"},{"id":"2508.12137","title":"Infusing fine-grained visual knowledge to Vision-Language Models","created":"2025-08-16","cited_by_count":2,"area":"mllm"},{"id":"2605.15961","title":"Sparse Autoencoders enable Robust and Interpretable Fine-tuning of CLIP models","created":"2026-05-15","cited_by_count":2,"area":"mllm"},{"id":"2606.06667","title":"The Piggyback Hypothesis of Generalization: Explaining and Mitigating Emergent Misalignment","created":"2026-06-04","cited_by_count":2,"area":null},{"id":"2407.06955","title":"ICLGuard: Controlling In-Context Learning Behavior for Applicability Authorization","created":"2024-07-09","cited_by_count":1,"area":null},{"id":"2407.15731","title":"The Inter-Intra Modal Measure: A Predictive Lens on Fine-Tuning Outcomes in Vision-Language Models","created":"2024-07-22","cited_by_count":1,"area":"mllm"},{"id":"2409.07582","title":"Minimizing Embedding Distortion for Robust Out-of-Distribution Performance","created":"2024-09-11","cited_by_count":1,"area":null},{"id":"2502.12930","title":"Universal Embedding Function for Traffic Classification via QUIC Domain Recognition Pretraining: A Transfer Learning Success","created":"2025-02-18","cited_by_count":1,"area":null},{"id":"2505.24088","title":"Proxy-FDA: Proxy-based Feature Distribution Alignment for Fine-tuning Vision Foundation Models without Forgetting","created":"2025-05-30","cited_by_count":1,"area":null},{"id":"2506.00676","title":"SafeTuneBed: A Toolkit for Benchmarking LLM Safety Alignment in Fine-Tuning","created":"2025-05-31","cited_by_count":1,"area":"alignment"},{"id":"2511.10683","title":"LT-Soups: Bridging Head and Tail Classes via Subsampled Model Soups","created":"2025-11-11","cited_by_count":1,"area":null},{"id":"2511.14901","title":"FarSLIP: Discovering Effective CLIP Adaptation for Fine-Grained Remote Sensing Understanding","created":"2025-11-18","cited_by_count":1,"area":null},{"id":"2603.24857","title":"AI Security in the Foundation Model Era: A Comprehensive Survey from a Unified Perspective","created":"2026-03-25","cited_by_count":1,"area":"safety"},{"id":"2603.25891","title":"Few Shots Text to Image Retrieval: New Benchmarking Dataset and Optimization Methods","created":"2026-03-26","cited_by_count":1,"area":"mllm"},{"id":"2606.20110","title":"FrozenDrive: Zero-Shot Text-Guided Driving Scene Generation and Data Augmentation with Parameter-Free Frozen Diffusion Model","created":"2026-06-18","cited_by_count":1,"area":"diffusion"},{"id":"2608.03855","title":"Bi-semantic Chemical Embedder for Joint Representation Learning of SMILES and Natural Language","created":"2026-08-04","cited_by_count":1,"area":null},{"id":"2410.16006","title":"Exploring Continual Fine-Tuning for Enhancing Language Ability in Large Language Model","created":"2024-10-21","cited_by_count":0,"area":null},{"id":"2503.19947","title":"Vanishing Depth: Training Generalized Depth Adapters with Sinusoidal Depth Preprocessing for Pretrained RGB Encoders","created":"2025-03-25","cited_by_count":0,"area":null},{"id":"2509.05328","title":"Feed Two Birds with One Scone: Exploiting Function-Space Regularization for Both OOD Robustness and ID Fine-Tuning Performance","created":"2025-08-31","cited_by_count":0,"area":null},{"id":"2509.14921","title":"Trade-offs in Cross-Domain Generalization of Foundation Model Fine-Tuned for Biometric Applications","created":"2025-09-18","cited_by_count":0,"area":null},{"id":"2511.09880","title":"EnchTable: Unified Safety Alignment Transfer in Fine-tuned Large Language Models","created":"2025-11-13","cited_by_count":0,"area":"alignment"},{"id":"2602.07532","title":"Evaluating Object-Centric Models beyond Object Discovery","created":"2026-02-07","cited_by_count":0,"area":null},{"id":"2602.17546","title":"Learning to Stay Safe: Adaptive Regularization Against Safety Degradation during Fine-Tuning","created":"2026-02-19","cited_by_count":0,"area":null},{"id":"2602.19449","title":"Decoupling Vision and Language: Codebook Anchored Visual Adaptation","created":"2026-02-23","cited_by_count":0,"area":"mllm"},{"id":"2605.05995","title":"Safety Anchor: Defending Harmful Fine-tuning via Geometric Bottlenecks","created":"2026-05-07","cited_by_count":0,"area":"alignment"},{"id":"2605.14194","title":"GradShield: Alignment Preserving Finetuning","created":"2026-05-13","cited_by_count":0,"area":null},{"id":"2605.24550","title":"Jailbreak to Protect: Buffering and Reinforcing via Temporary Jailbreaking for Safe Fine-Tuning in Large Language Models","created":"2026-05-23","cited_by_count":0,"area":"safety"},{"id":"2606.07970","title":"Defending Against Malicious Finetuning by Scaling Train-time Adversarial Attacks","created":"2026-06-06","cited_by_count":0,"area":"alignment"},{"id":"2606.16256","title":"KeepLoRA++: Continual Learning with Layer-Scaled Residual Gradient Adaptation","created":"2026-06-15","cited_by_count":0,"area":"mllm"},{"id":"2609.32676","title":"SIFT: Enhancing Time Series Foundation Models via Semantic Invariance and Structural Fidelity Fine-Tuning","created":"2026-09-26","cited_by_count":0,"area":null},{"id":"2610.04670","title":"A Tropical Geometry View of Forgetting: A Per-Unit Projector for Knowledge-Preserving Fine-Tuning","created":"2026-10-03","cited_by_count":0,"area":null},{"id":"2610.10345","title":"SLDR: Defending Against Malicious Fine-tuning via Selective Layers Recovery and Dynamic Routing","created":"2026-10-07","cited_by_count":0,"area":"alignment"},{"id":"2610.13578","title":"RARA: Robust Policy Fine-Tuning through Retrieval-Anchored Representation Alignment for Robotic Manipulation","created":"2026-10-09","cited_by_count":0,"area":"vla"},{"id":"2610.17713","title":"Confine to the Task, Anchor the Rest: Concept-Guided Retention Regularizer for Parameter-Efficient Fine-Tuning","created":"2026-10-13","cited_by_count":0,"area":null}],"next_cursor":null}