{"total":124,"rows":[{"id":"2404.14219","title":"Phi-3 Technical Report: A Highly Capable Language Model Locally on Your Phone","created":"2024-04-22","cited_by_count":1917,"area":null},{"id":"2412.08905","title":"Phi-4 Technical Report","created":"2024-12-12","cited_by_count":711,"area":null},{"id":"2311.06668","title":"In-context Vectors: Making In Context Learning More Effective and Controllable Through Latent Space Steering","created":"2023-11-11","cited_by_count":245,"area":null},{"id":"2309.13788","title":"Can LLM-Generated Misinformation Be Detected?","created":"2023-09-25","cited_by_count":177,"area":null},{"id":"2402.09283","title":"Attacks, Defenses and Evaluations for LLM Conversation Safety: A Survey","created":"2024-02-14","cited_by_count":130,"area":null},{"id":"2405.16833","title":"Safe LoRA: the Silver Lining of Reducing Safety Risks when Fine-tuning Large Language Models","created":"2024-05-27","cited_by_count":125,"area":null},{"id":"2407.18418","title":"Know Your Limits: A Survey of Abstention in Large Language Models","created":"2024-07-25","cited_by_count":121,"area":null},{"id":"2407.12043","title":"The Art of Saying No: Contextual Noncompliance in Language Models","created":"2024-07-02","cited_by_count":105,"area":null},{"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":"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":"2406.20053","title":"Covert Malicious Finetuning: Challenges in Safeguarding LLM Adaptation","created":"2024-06-28","cited_by_count":80,"area":null},{"id":"2403.15246","title":"FollowIR: Evaluating and Teaching Information Retrieval Models to Follow Instructions","created":"2024-03-22","cited_by_count":69,"area":null},{"id":"2407.09121","title":"Refuse Whenever You Feel Unsafe: Improving Safety in LLMs via Decoupled Refusal Training","created":"2024-07-12","cited_by_count":69,"area":null},{"id":"2401.00287","title":"The Art of Defending: A Systematic Evaluation and Analysis of LLM Defense Strategies on Safety and Over-Defensiveness","created":"2023-12-30","cited_by_count":67,"area":null},{"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":"2404.12241","title":"Introducing v0.5 of the AI Safety Benchmark from MLCommons","created":"2024-04-18","cited_by_count":62,"area":null},{"id":"2508.09224","title":"From Hard Refusals to Safe-Completions: Toward Output-Centric Safety Training","created":"2025-08-12","cited_by_count":52,"area":null},{"id":"2402.04247","title":"Risks of AI Scientists: Prioritizing Safeguarding Over Autonomy","created":"2024-02-06","cited_by_count":49,"area":null},{"id":"2410.03415","title":"Surgical, Cheap, and Flexible: Mitigating False Refusal in Language Models via Single Vector Ablation","created":"2024-10-04","cited_by_count":48,"area":null},{"id":"2403.03744","title":"MedSafetyBench: Evaluating and Improving the Medical Safety of Large Language Models","created":"2024-03-06","cited_by_count":44,"area":null},{"id":"2403.04786","title":"Breaking Down the Defenses: A Comparative Survey of Attacks on Large Language Models","created":"2024-03-03","cited_by_count":44,"area":null},{"id":"2504.16980","title":"Safety Pretraining: Toward the Next Generation of Safe AI","created":"2025-04-23","cited_by_count":43,"area":null},{"id":"2505.17306","title":"Refusal Direction is Universal Across Safety-Aligned Languages","created":"2025-05-22","cited_by_count":38,"area":null},{"id":"2406.07243","title":"MBBQ: A Dataset for Cross-Lingual Comparison of Stereotypes in Generative LLMs","created":"2024-06-11","cited_by_count":35,"area":null},{"id":"2410.10014","title":"Safety-Aware Fine-Tuning of Large Language Models","created":"2024-10-13","cited_by_count":34,"area":null},{"id":"2407.03963","title":"LLM-jp: A Cross-organizational Project for the Research and Development of Fully Open Japanese LLMs","created":"2024-07-04","cited_by_count":33,"area":null},{"id":"2502.15851","title":"Control Illusion: The Failure of Instruction Hierarchies in Large Language Models","created":"2025-02-21","cited_by_count":33,"area":null},{"id":"2406.11852","title":"Risks from Language Models for Automated Mental Healthcare: Ethics and Structure for Implementation","created":"2024-04-02","cited_by_count":27,"area":null},{"id":"2410.01518","title":"InfiniPot: Infinite Context Processing on Memory-Constrained LLMs","created":"2024-10-02","cited_by_count":27,"area":null},{"id":"2406.06369","title":"Annotation alignment: Comparing LLM and human annotations of conversational safety","created":"2024-06-10","cited_by_count":23,"area":null},{"id":"2410.10343","title":"Locking Down the Finetuned LLMs Safety","created":"2024-10-14","cited_by_count":22,"area":null},{"id":"2502.20968","title":"Beware of Your Po! Measuring and Mitigating AI Safety Risks in Role-Play Fine-Tuning of LLMs","created":"2025-02-28","cited_by_count":22,"area":null},{"id":"2311.02105","title":"Making Harmful Behaviors Unlearnable for Large Language Models","created":"2023-11-02","cited_by_count":20,"area":null},{"id":"2404.07900","title":"High-Dimension Human Value Representation in Large Language Models","created":"2024-04-11","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":"2504.07448","title":"LoRI: Reducing Cross-Task Interference in Multi-Task Low-Rank Adaptation","created":"2025-04-10","cited_by_count":19,"area":null},{"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":"2505.12038","title":"Safe Delta: Consistently Preserving Safety when Fine-Tuning LLMs on Diverse Datasets","created":"2025-05-17","cited_by_count":18,"area":null},{"id":"2410.10801","title":"Mix Data or Merge Models? Optimizing for Diverse Multi-Task Learning","created":"2024-10-14","cited_by_count":17,"area":null},{"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":"2503.20807","title":"Fundamental Safety-Capability Trade-offs in Fine-tuning Large Language Models","created":"2025-03-24","cited_by_count":17,"area":null},{"id":"2405.11290","title":"MBIAS: Mitigating Bias in Large Language Models While Retaining Context","created":"2024-05-18","cited_by_count":15,"area":null},{"id":"2502.02958","title":"Position: Editing Large Language Models Poses Serious Safety Risks","created":"2025-02-05","cited_by_count":15,"area":null},{"id":"2407.03234","title":"Self-Evaluation as a Defense Against Adversarial Attacks on LLMs","created":"2024-07-03","cited_by_count":14,"area":null},{"id":"2412.06748","title":"Refusal Tokens: A Simple Way to Calibrate Refusals in Large Language Models","created":"2024-12-09","cited_by_count":14,"area":null},{"id":"2504.01205","title":"Epistemic Alignment: A Mediating Framework for User-LLM Knowledge Delivery","created":"2025-04-01","cited_by_count":14,"area":null},{"id":"2404.17047","title":"Near to Mid-term Risks and Opportunities of Open-Source Generative AI","created":"2024-04-25","cited_by_count":13,"area":null},{"id":"2405.02411","title":"The Call for Socially Aware Language Technologies","created":"2024-05-03","cited_by_count":13,"area":null},{"id":"2405.08597","title":"Risks and Opportunities of Open-Source Generative AI","created":"2024-05-14","cited_by_count":13,"area":null},{"id":"2408.11727","title":"Efficient Detection of Toxic Prompts in Large Language Models","created":"2024-08-21","cited_by_count":13,"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":"2502.16776","title":"AISafetyLab: A Comprehensive Framework for AI Safety Evaluation and Improvement","created":"2025-02-24","cited_by_count":12,"area":null},{"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":"2401.02575","title":"Large Language Models for Social Networks: Applications, Challenges, and Solutions","created":"2024-01-04","cited_by_count":11,"area":null},{"id":"2412.19512","title":"Safeguard Fine-Tuned LLMs Through Pre- and Post-Tuning Model Merging","created":"2024-12-27","cited_by_count":11,"area":null},{"id":"2404.00399","title":"Aurora-M: Open Source Continual Pre-training for Multilingual Language and Code","created":"2024-03-30","cited_by_count":10,"area":null},{"id":"2407.11733","title":"How Are LLMs Mitigating Stereotyping Harms? Learning from Search Engine Studies","created":"2024-07-16","cited_by_count":10,"area":null},{"id":"2505.21344","title":"The Multilingual Divide and Its Impact on Global AI Safety","created":"2025-05-27","cited_by_count":10,"area":null},{"id":"2408.06663","title":"Amuro and Char: Analyzing the Relationship between Pre-Training and Fine-Tuning of Large Language Models","created":"2024-08-13","cited_by_count":9,"area":null},{"id":"2404.01399","title":"Developing Safe and Responsible Large Language Model : Can We Balance Bias Reduction and Language Understanding in Large Language Models?","created":"2024-04-01","cited_by_count":8,"area":null},{"id":"2405.15202","title":"Cross-Task Defense: Instruction-Tuning LLMs for Content Safety","created":"2024-05-24","cited_by_count":8,"area":null},{"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":"2411.08243","title":"Beyond the Safety Bundle: Auditing the Helpful and Harmless Dataset","created":"2024-11-12","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":"2501.17132","title":"ASTRAL: Automated Safety Testing of Large Language Models","created":"2025-01-28","cited_by_count":7,"area":null},{"id":"2506.02573","title":"IndoSafety: Culturally Grounded Safety for LLMs in Indonesian Languages","created":"2025-06-03","cited_by_count":7,"area":null},{"id":"2509.06795","title":"Anchoring Refusal Direction: Mitigating Safety Risks in Tuning via Projection Constraint","created":"2025-09-08","cited_by_count":7,"area":null},{"id":"2409.03274","title":"Recent Advances in Attack and Defense Approaches of Large Language Models","created":"2024-09-05","cited_by_count":6,"area":null},{"id":"2510.00857","title":"ManagerBench: Evaluating the Safety-Pragmatism Trade-off in Autonomous LLMs","created":"2025-10-01","cited_by_count":6,"area":null},{"id":"2601.15220","title":"Privacy Collapse: Benign Fine-Tuning Can Break Contextual Privacy in Language Models","created":"2026-01-21","cited_by_count":6,"area":null},{"id":"2511.18852","title":"FanarGuard: A Culturally-Aware Moderation Filter for Arabic Language Models","created":"2025-11-24","cited_by_count":5,"area":null},{"id":"2407.12999","title":"Securing the Future of GenAI: Policy and Technology","created":"2024-05-21","cited_by_count":4,"area":null},{"id":"2410.10852","title":"SafeLLM: Domain-Specific Safety Monitoring for Large Language Models: A Case Study of Offshore Wind Maintenance","created":"2024-10-06","cited_by_count":4,"area":null},{"id":"2412.06843","title":"Semantic Loss Guided Data Efficient Supervised Fine Tuning for Safe Responses in LLMs","created":"2024-12-07","cited_by_count":4,"area":null},{"id":"2501.06208","title":"Enhancing AI Safety Through the Fusion of Low Rank Adapters","created":"2024-12-30","cited_by_count":4,"area":null},{"id":"2602.11137","title":"Weight Decay Improves Language Model Plasticity","created":"2026-02-11","cited_by_count":4,"area":null},{"id":"2406.04220","title":"BEADs: Bias Evaluation Across Domains","created":"2024-06-06","cited_by_count":3,"area":null},{"id":"2408.12959","title":"Multimodal Contrastive In-Context Learning","created":"2024-08-23","cited_by_count":3,"area":null},{"id":"2412.16469","title":"Chained Tuning Leads to Biased Forgetting","created":"2024-12-21","cited_by_count":3,"area":null},{"id":"2506.13593","title":"Calibrated Predictive Lower Bounds on Time-to-Unsafe-Sampling in LLMs","created":"2025-06-16","cited_by_count":3,"area":null},{"id":"2603.01185","title":"Token-level Data Selection for Safe LLM Fine-tuning","created":"2026-03-01","cited_by_count":3,"area":null},{"id":"2606.03330","title":"FLIPS: Instance-Fingerprinting for LLMs via Pseudo-random Sequences","created":"2026-06-02","cited_by_count":3,"area":null},{"id":"2410.23472","title":"Risk Sources and Risk Management Measures in Support of Standards for General-Purpose AI Systems","created":"2024-10-30","cited_by_count":2,"area":null},{"id":"2412.07430","title":"Knowledge Graph Guided Evaluation of Abstention Techniques","created":"2024-12-10","cited_by_count":2,"area":null},{"id":"2412.18551","title":"Libra-Leaderboard: Towards Responsible AI through a Balanced Leaderboard of Safety and Capability","created":"2024-12-24","cited_by_count":2,"area":null},{"id":"2506.03230","title":"DiaBlo: Diagonal Blocks Are Sufficient For Finetuning","created":"2025-06-03","cited_by_count":2,"area":null},{"id":"2511.21056","title":"Bilevel Data Curation for LLM Fine-tuning: Offline Selection and Online Self-Refining Generation","created":"2025-11-26","cited_by_count":2,"area":null},{"id":"2604.06233","title":"Blind Refusal: Language Models Refuse to Help Users Evade Unjust, Absurd, and Illegitimate Rules","created":"2026-04-03","cited_by_count":2,"area":null},{"id":"2605.29267","title":"When and How Human Curation Backfires: Preference Alignment under Multi-Model Self-Consuming Loop","created":"2026-05-28","cited_by_count":2,"area":null},{"id":"2608.28327","title":"Layered LLM Defenses as an Ensemble: Access Tiers, Inference Cost, and the Measured Failure Correlation Between Defense Layers","created":"2026-08-28","cited_by_count":2,"area":null},{"id":"2410.02230","title":"Mitigating Downstream Model Risks via Model Provenance","created":"2024-10-03","cited_by_count":1,"area":null},{"id":"2412.08147","title":"Variational Model Merging for Pareto Front Estimation in Multitask Finetuning","created":"2024-12-11","cited_by_count":1,"area":null},{"id":"2502.01436","title":"Towards Safer Chatbots: Automated Policy Compliance Evaluation of Custom GPTs","created":"2025-02-03","cited_by_count":1,"area":null},{"id":"2506.19140","title":"Command-V: Pasting LLM Behaviors via Activation Profiles","created":"2025-06-23","cited_by_count":1,"area":null},{"id":"2508.20333","title":"Poison Once, Refuse Forever: Weaponizing Alignment for Injecting Bias in LLMs","created":"2025-08-28","cited_by_count":1,"area":null},{"id":"2509.06807","title":"MoGU V2: Toward a Higher Pareto Frontier Between Model Usability and Security","created":"2025-09-08","cited_by_count":1,"area":null},{"id":"2510.21885","title":"Preventing Catastrophic Forgetting: Behavior-Aware Sampling for Safer Language Model Fine-Tuning","created":"2025-10-23","cited_by_count":1,"area":null},{"id":"2601.23094","title":"Safer Policy Compliance with Dynamic Epistemic Fallback","created":"2026-01-30","cited_by_count":1,"area":null},{"id":"2602.13033","title":"Buy versus Build an LLM: A Decision Framework for Governments","created":"2026-02-13","cited_by_count":1,"area":null},{"id":"2604.26577","title":"Benchmarking the Safety of Large Language Models for Robotic Health Attendant Control","created":"2026-04-29","cited_by_count":1,"area":null}],"next_cursor":"100"}