{"total":76,"rows":[{"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":"2409.20089","title":"Robust LLM safeguarding via refusal feature adversarial training","created":"2024-09-30","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":"2510.26243","title":"Angular Steering: Behavior Control via Rotation in Activation Space","created":"2025-10-30","cited_by_count":53,"area":null},{"id":"2410.13341","title":"Limits to scalable evaluation at the frontier: LLM as Judge won't beat twice the data","created":"2024-10-17","cited_by_count":51,"area":null},{"id":"2502.05209","title":"Model Tampering Attacks Enable More Rigorous Evaluations of LLM Capabilities","created":"2025-02-03","cited_by_count":39,"area":null},{"id":"2506.11094","title":"The Scales of Justitia: A Comprehensive Survey on Safety Evaluation of LLMs","created":"2025-06-06","cited_by_count":26,"area":null},{"id":"2506.14261","title":"RL-Obfuscation: Can Language Models Learn to Evade Latent-Space Monitors?","created":"2025-06-17","cited_by_count":24,"area":null},{"id":"2502.16797","title":"Forecasting Rare Language Model Behaviors","created":"2025-02-24","cited_by_count":19,"area":null},{"id":"2502.02260","title":"Position: Adversarial ML for LLMs Is Not Making Any Progress","created":"2025-02-04","cited_by_count":15,"area":null},{"id":"2506.24068","title":"STACK: Adversarial Attacks on LLM Safeguard Pipelines","created":"2025-06-30","cited_by_count":14,"area":null},{"id":"2602.20031","title":"Latent Introspection: Models Can Detect Prior Concept Injections","created":"2026-02-23","cited_by_count":14,"area":null},{"id":"2508.17158","title":"Towards Safeguarding LLM Fine-tuning APIs against Cipher Attacks","created":"2025-08-23","cited_by_count":11,"area":null},{"id":"2506.06414","title":"Benchmarking Misuse Mitigation Against Covert Adversaries","created":"2025-06-06","cited_by_count":8,"area":null},{"id":"2603.01919","title":"Real Money, Fake Models: Deceptive Model Claims in Shadow APIs","created":"2026-03-02","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":"2507.06253","title":"Emergent misalignment as prompt sensitivity: A research note","created":"2025-07-06","cited_by_count":6,"area":null},{"id":"2604.24074","title":"How Sensitive Are Safety Benchmarks to Judge Configuration Choices?","created":"2026-04-27","cited_by_count":5,"area":null},{"id":"2608.28945","title":"Automated Researchers Can Mitigate Well-characterized Alignment Failures","created":"2026-08-28","cited_by_count":5,"area":null},{"id":"2605.21602","title":"Benchmarking and Improving Monitors for Out-Of-Distribution Alignment Failure in LLMs","created":"2026-05-20","cited_by_count":4,"area":null},{"id":"2605.28591","title":"Models That Know How Evaluations Are Designed Score Safer","created":"2026-05-27","cited_by_count":4,"area":null},{"id":"2512.08946","title":"Large Language Models as Search Engines: Societal Challenges","created":"2025-11-24","cited_by_count":3,"area":null},{"id":"2602.14135","title":"ForesightSafety Bench: A Frontier Risk Evaluation and Governance Framework towards Safe AI","created":"2026-02-15","cited_by_count":3,"area":null},{"id":"2602.16729","title":"Intent Laundering: AI Safety Datasets Are Not What They Seem","created":"2026-02-17","cited_by_count":3,"area":null},{"id":"2605.20296","title":"Spectral Unforgetting: Post-Hoc Recovery of Damaged Capabilities Without Retraining","created":"2026-05-19","cited_by_count":3,"area":null},{"id":"2606.07874","title":"Safety is Contextual, LLM-Judges Are Not: Navigating the Rigid Priors of Evaluators","created":"2026-06-05","cited_by_count":3,"area":null},{"id":"2506.20251","title":"Q-resafe: Assessing Safety Risks and Quantization-aware Safety Patching for Quantized Large Language Models","created":"2025-06-25","cited_by_count":2,"area":null},{"id":"2507.11544","title":"The Safety Gap Toolkit: Evaluating Hidden Dangers of Open-Source Models","created":"2025-07-08","cited_by_count":2,"area":null},{"id":"2605.12199","title":"Overtrained, Not Misaligned","created":"2026-05-12","cited_by_count":2,"area":null},{"id":"2605.14605","title":"A Few Steps Further: Why Defenses Against Malicious Finetuning Erode Under Continued Training","created":"2026-05-14","cited_by_count":2,"area":null},{"id":"2605.24229","title":"How Well Do Models Follow Their Constitutions?","created":"2026-05-22","cited_by_count":2,"area":null},{"id":"2605.28830","title":"Benchmarking Open-Source Safety Guard Models: A Comprehensive Evaluation","created":"2026-04-10","cited_by_count":2,"area":null},{"id":"2606.03810","title":"Consistency Training Can Entrench Misalignment","created":"2026-06-02","cited_by_count":2,"area":null},{"id":"2608.02684","title":"A Blind Spot in Alignment: Quantifying Biosecurity Risks in Large Language Models","created":"2026-08-03","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":"2508.18646","title":"Beyond Benchmarks: LLM Evaluation with an Anthropomorphic and Lifecycle-oriented Roadmap","created":"2025-08-26","cited_by_count":1,"area":null},{"id":"2602.02557","title":"The Alignment Curse: Modality Alignment Supercharges Audio Attacks via Text Transfer","created":"2026-01-30","cited_by_count":1,"area":null},{"id":"2604.07655","title":"Guardian-as-an-Advisor: Advancing Next-Generation Guardian Models for Trustworthy LLMs","created":"2026-04-08","cited_by_count":1,"area":null},{"id":"2604.11120","title":"Persona Non Grata: Single-Method Safety Evaluation Is Incomplete for Persona-Imbued LLMs","created":"2026-04-13","cited_by_count":1,"area":null},{"id":"2605.05789","title":"Stego Battlefield: Evaluating Image Steganography Attacks and Steganalysis Defenses","created":"2026-05-07","cited_by_count":1,"area":null},{"id":"2605.15118","title":"Talk is (Not) Cheap: A Taxonomy and Benchmark Coverage Audit for LLM Attacks","created":"2026-05-14","cited_by_count":1,"area":null},{"id":"2606.03344","title":"RogueMerge: Robust and Unified Attacks against LLM Model Merging","created":"2026-06-02","cited_by_count":1,"area":null},{"id":"2606.09068","title":"Emergent Misalignment Can Be Induced by Sycophancy and Reversed via Alignment Gating","created":"2026-06-08","cited_by_count":1,"area":null},{"id":"2607.10455","title":"ANCHOR: Automated Alignment Auditing for CLI Agents on Real-World Harm","created":"2026-07-11","cited_by_count":1,"area":null},{"id":"2607.13039","title":"Safeguard-Conditioned Uplift: Measuring Utility-Risk Frontiers for Dual-Use Biology Assistants","created":"2026-06-12","cited_by_count":1,"area":null},{"id":"2607.18665","title":"SciHazard: A Benchmark for Measuring Scientific Safety Risks with Decomposed Harm Scoring","created":"2026-07-21","cited_by_count":1,"area":null},{"id":"2607.21063","title":"QuantiBias: Benchmarking Quantization-Induced Bias in LLMs","created":"2026-07-23","cited_by_count":1,"area":null},{"id":"2608.13482","title":"Synthetic Persona Pretraining: Alignment from Token Zero","created":"2026-08-13","cited_by_count":1,"area":null},{"id":"2609.00092","title":"Safin-1: Safety from Within through Memory-Native State Evolution","created":"2026-08-31","cited_by_count":1,"area":null},{"id":"2510.17918","title":"JT-Safe: Intrinsically Enhancing the Safety and Trustworthiness of LLMs","created":"2025-10-20","cited_by_count":0,"area":null},{"id":"2602.02708","title":"BinaryPPO: Efficient Policy Optimization for Binary Classification","created":"2026-02-02","cited_by_count":0,"area":null},{"id":"2602.15238","title":"Closing the Distribution Gap in Adversarial Training for LLMs","created":"2026-02-16","cited_by_count":0,"area":null},{"id":"2604.00324","title":"The Persistent Vulnerability of Aligned AI Systems","created":"2026-03-31","cited_by_count":0,"area":null},{"id":"2604.05872","title":"Swiss-Bench 003: Evaluating LLM Reliability and Adversarial Security for Swiss Regulatory Contexts","created":"2026-04-07","cited_by_count":0,"area":null},{"id":"2604.17614","title":"Characterizing Model-Native Skills","created":"2026-04-19","cited_by_count":0,"area":null},{"id":"2605.10639","title":"Navigating the Sea of LLM Evaluation: Investigating Bias in Toxicity Benchmarks","created":"2026-05-11","cited_by_count":0,"area":null},{"id":"2605.20262","title":"Residual Paving: Diagnosing the Routing Bottleneck in Selective Refusal Editing","created":"2026-05-18","cited_by_count":0,"area":null},{"id":"2605.24414","title":"JT-SAFE-V2: Safety-by-Design Foundation Model with World-Context Data","created":"2026-05-23","cited_by_count":0,"area":null},{"id":"2606.08629","title":"Sycophancy Towards Researchers Drives Performative Misalignment","created":"2026-06-07","cited_by_count":0,"area":null},{"id":"2606.20626","title":"Efficient Safety Benchmarking via Item Response Theory","created":"2026-05-26","cited_by_count":0,"area":null},{"id":"2607.02396","title":"Fast Multi-dimensional Refusal Subspaces via RFM-AGOP","created":"2026-07-02","cited_by_count":0,"area":null},{"id":"2607.20558","title":"StabilityBench: Benchmarking Instability in LLMs","created":"2026-07-17","cited_by_count":0,"area":null},{"id":"2607.22671","title":"AIR-BENCH Live: An Evolving Safety Benchmark for Foundation Models","created":"2026-07-06","cited_by_count":0,"area":null},{"id":"2608.04347","title":"Introspecting Alignment Shifts Beyond Behaviors Implanted Through Fine-Tuning","created":"2026-08-05","cited_by_count":0,"area":null},{"id":"2609.00578","title":"Same Request, Different Boundary: Evaluating Cybersecurity Assistance across Conversational Contexts","created":"2026-09-01","cited_by_count":0,"area":null},{"id":"2609.01210","title":"Who Judges the Judges? A Chinese Safety QA Benchmark for Evaluating LLM Responses and Safety Judges","created":"2026-09-01","cited_by_count":0,"area":null},{"id":"2609.01611","title":"EvalDetectBench: A Benchmark for Measuring Evaluation Awareness in Frontier Language Models","created":"2026-06-08","cited_by_count":0,"area":null},{"id":"2609.22153","title":"SafeTune: A Unified Faithful Library for Auditing and Repairing Safety Drift in Fine-Tuned LLMs","created":"2026-08-26","cited_by_count":0,"area":null},{"id":"2609.32547","title":"Prioritizing Repeated LLM Evaluation for Hidden Failure Discovery","created":"2026-09-26","cited_by_count":0,"area":null},{"id":"2609.35028","title":"VEX-Bench: Benchmarking Verification Complexity of LLM-Generated Misinformation","created":"2026-09-28","cited_by_count":0,"area":null},{"id":"2609.35261","title":"Imprint Reader: From Weight-Update Readout to Behavioral Intervention","created":"2026-09-28","cited_by_count":0,"area":null},{"id":"2609.36316","title":"Training LLMs to Verbalize Evaluation Awareness","created":"2026-09-28","cited_by_count":0,"area":null},{"id":"2609.39788","title":"Safety of Latent Communication in Multi-Agent Systems","created":"2026-09-30","cited_by_count":0,"area":null},{"id":"2610.01535","title":"False Floors: LLM Safety Routing Evaluations Break Under Distribution Shift","created":"2026-10-01","cited_by_count":0,"area":null},{"id":"2610.04316","title":"From Latent Space to Jacobian Space: Measuring, Evading, and Training Against Safety-Content Accessibility","created":"2026-10-03","cited_by_count":0,"area":null},{"id":"2610.17728","title":"Safety for Whom? Benchmarking Understanding Beyond Refusal in Egocentric Multimodal Assistants","created":"2026-10-13","cited_by_count":0,"area":null}],"next_cursor":null}