{"total":186,"rows":[{"id":"2412.04984","title":"Frontier Models are Capable of In-context Scheming","created":"2024-12-06","cited_by_count":287,"area":null},{"id":"2402.01613","title":"Nomic Embed: Training a Reproducible Long Context Text Embedder","created":"2024-02-02","cited_by_count":265,"area":null},{"id":"2406.10162","title":"Sycophancy to Subterfuge: Investigating Reward-Tampering in Large Language Models","created":"2024-06-14","cited_by_count":178,"area":null},{"id":"2406.07358","title":"AI Sandbagging: Language Models can Strategically Underperform on Evaluations","created":"2024-06-11","cited_by_count":145,"area":null},{"id":"2401.14446","title":"Black-Box Access is Insufficient for Rigorous AI Audits","created":"2024-01-25","cited_by_count":126,"area":null},{"id":"2507.14805","title":"Subliminal Learning: Language models transmit behavioral traits via hidden signals in data","created":"2025-07-20","cited_by_count":95,"area":null},{"id":"2506.11613","title":"Model Organisms for Emergent Misalignment","created":"2025-06-13","cited_by_count":91,"area":null},{"id":"2506.19823","title":"Persona Features Control Emergent Misalignment","created":"2025-06-24","cited_by_count":86,"area":null},{"id":"2407.13692","title":"Prover-Verifier Games improve legibility of LLM outputs","created":"2024-07-18","cited_by_count":85,"area":null},{"id":"2407.12831","title":"Truth is Universal: Robust Detection of Lies in LLMs","created":"2024-07-03","cited_by_count":79,"area":null},{"id":"2405.03644","title":"When LLMs Meet Cybersecurity: A Systematic Literature Review","created":"2024-05-06","cited_by_count":71,"area":null},{"id":"2506.11618","title":"Convergent Linear Representations of Emergent Misalignment","created":"2025-06-13","cited_by_count":71,"area":null},{"id":"2401.12255","title":"Instructional Fingerprinting of Large Language Models","created":"2024-01-21","cited_by_count":68,"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":"2402.00786","title":"CroissantLLM: A Truly Bilingual French-English Language Model","created":"2024-02-01","cited_by_count":53,"area":null},{"id":"2406.06144","title":"Language Models Resist Alignment: Evidence From Data Compression","created":"2024-06-10","cited_by_count":53,"area":null},{"id":"2410.21514","title":"Sabotage Evaluations for Frontier Models","created":"2024-10-28","cited_by_count":52,"area":null},{"id":"2410.13722","title":"Persistent Pre-Training Poisoning of LLMs","created":"2024-10-17","cited_by_count":48,"area":null},{"id":"2405.19550","title":"Stress-Testing Capability Elicitation With Password-Locked Models","created":"2024-05-29","cited_by_count":46,"area":null},{"id":"2405.01576","title":"Uncovering Deceptive Tendencies in Language Models: A Simulated Company AI Assistant","created":"2024-04-25","cited_by_count":38,"area":null},{"id":"2407.10887","title":"Hey, That's My Model! Introducing Chain & Hash, An LLM Fingerprinting Technique","created":"2024-07-15","cited_by_count":37,"area":null},{"id":"2402.16382","title":"Immunization against harmful fine-tuning attacks","created":"2024-02-26","cited_by_count":35,"area":null},{"id":"2406.19370","title":"Emergence of Hidden Capabilities: Exploring Learning Dynamics in Concept Space","created":"2024-06-27","cited_by_count":35,"area":null},{"id":"2507.01786","title":"Probing and Steering Evaluation Awareness of Language Models","created":"2025-07-02","cited_by_count":35,"area":null},{"id":"2404.01231","title":"Privacy Backdoors: Enhancing Membership Inference through Poisoning Pre-trained Models","created":"2024-04-01","cited_by_count":30,"area":null},{"id":"2505.18889","title":"Security Concerns for Large Language Models: A Survey","created":"2025-05-24","cited_by_count":29,"area":null},{"id":"2510.13900","title":"Narrow Finetuning Leaves Clearly Readable Traces in Activation Differences","created":"2025-10-14","cited_by_count":28,"area":null},{"id":"2403.00108","title":"LoRATK: LoRA Once, Backdoor Everywhere in the Share-and-Play Ecosystem","created":"2024-02-29","cited_by_count":24,"area":null},{"id":"2406.13261","title":"BeHonest: Benchmarking Honesty in Large Language Models","created":"2024-06-19","cited_by_count":24,"area":null},{"id":"2412.01784","title":"Noise Injection Reveals Hidden Capabilities of Sandbagging Language Models","created":"2024-12-02","cited_by_count":24,"area":null},{"id":"2602.07852","title":"Emergent Misalignment is Easy, Narrow Misalignment is Hard","created":"2026-02-08","cited_by_count":23,"area":null},{"id":"2512.08093","title":"Training LLMs for Honesty via Confessions","created":"2025-12-08","cited_by_count":22,"area":null},{"id":"2403.15115","title":"Language Models in Dialogue: Conversational Maxims for Human-AI Interactions","created":"2024-03-22","cited_by_count":21,"area":null},{"id":"2407.12858","title":"Grounding and Evaluation for Large Language Models: Practical Challenges and Lessons Learned (Survey)","created":"2024-07-10","cited_by_count":20,"area":null},{"id":"2409.19998","title":"Do Influence Functions Work on Large Language Models?","created":"2024-09-30","cited_by_count":20,"area":null},{"id":"2504.07863","title":"Robust Hallucination Detection in LLMs via Adaptive Token Selection","created":"2025-04-10","cited_by_count":19,"area":null},{"id":"2502.02180","title":"The Elicitation Game: Evaluating Capability Elicitation Techniques","created":"2025-02-04","cited_by_count":18,"area":null},{"id":"2505.14633","title":"Will AI Tell Lies to Save Sick Children? Litmus-Testing AI Values Prioritization with AIRiskDilemmas","created":"2025-05-20","cited_by_count":18,"area":null},{"id":"2405.19524","title":"AI Risk Management Should Incorporate Both Safety and Security","created":"2024-05-29","cited_by_count":17,"area":null},{"id":"2501.17858","title":"Improving Your Model Ranking on Chatbot Arena by Vote Rigging","created":"2025-01-29","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":"2604.25891","title":"Conditional misalignment: common interventions can hide emergent misalignment behind contextual triggers","created":"2026-04-28","cited_by_count":17,"area":null},{"id":"2502.00706","title":"Model Provenance Testing for Large Language Models","created":"2025-02-02","cited_by_count":15,"area":null},{"id":"2604.17596","title":"Terminal Wrench: A Dataset of 331 Reward-Hackable Environments and 3,632 Exploit Trajectories","created":"2026-04-19","cited_by_count":15,"area":null},{"id":"2502.07760","title":"Scalable Fingerprinting of Large Language Models","created":"2025-02-11","cited_by_count":14,"area":null},{"id":"2604.11806","title":"Detecting Safety Violations Across Many Agent Traces","created":"2026-04-13","cited_by_count":14,"area":null},{"id":"2405.05466","title":"Poser: Unmasking Alignment Faking LLMs by Manipulating Their Internals","created":"2024-05-08","cited_by_count":13,"area":null},{"id":"2410.16638","title":"LLMScan: Causal Scan for LLM Misbehavior Detection","created":"2024-10-22","cited_by_count":13,"area":null},{"id":"2407.09221","title":"Evaluating AI Evaluation: Perils and Prospects","created":"2024-07-12","cited_by_count":11,"area":null},{"id":"2506.20702","title":"The Singapore Consensus on Global AI Safety Research Priorities","created":"2025-06-25","cited_by_count":10,"area":null},{"id":"2510.14318","title":"Evaluating & Reducing Deceptive Dialogue From Language Models with Multi-turn RL","created":"2025-10-16","cited_by_count":10,"area":null},{"id":"2404.13060","title":"The Necessity of AI Audit Standards Boards","created":"2024-04-11","cited_by_count":9,"area":null},{"id":"2505.17441","title":"Discovering Forbidden Topics in Language Models","created":"2025-05-23","cited_by_count":9,"area":null},{"id":"2505.24842","title":"Cascading Adversarial Bias from Injection to Distillation in Language Models","created":"2025-05-30","cited_by_count":9,"area":null},{"id":"2507.23221","title":"A Single Direction of Truth: An Observer Model's Linear Residual Probe Exposes and Steers Contextual Hallucinations","created":"2025-07-31","cited_by_count":9,"area":null},{"id":"2510.15624","title":"Build Your Personalized Research Group: A Multiagent Framework for Continual and Interactive Science Automation","created":"2025-10-17","cited_by_count":9,"area":null},{"id":"2407.02596","title":"Towards More Realistic Extraction Attacks: An Adversarial Perspective","created":"2024-07-02","cited_by_count":8,"area":null},{"id":"2412.13341","title":"Concept-ROT: Poisoning Concepts in Large Language Models with Model Editing","created":"2024-12-17","cited_by_count":8,"area":null},{"id":"2506.06518","title":"A Systematic Review of Poisoning Attacks Against Large Language Models","created":"2025-06-06","cited_by_count":8,"area":null},{"id":"2410.09838","title":"Uncovering, Explaining, and Mitigating the Superficial Safety of Backdoor Defense","created":"2024-10-13","cited_by_count":7,"area":null},{"id":"2504.20084","title":"AI Awareness","created":"2025-04-25","cited_by_count":7,"area":null},{"id":"2510.03999","title":"LH-Deception: Simulating and Understanding LLM Deceptive Behaviors in Long-Horizon Interactions","created":"2025-10-05","cited_by_count":7,"area":null},{"id":"2604.07821","title":"More Capable, Less Cooperative? When LLMs Fail At Zero-Cost Collaboration","created":"2026-04-09","cited_by_count":7,"area":null},{"id":"2605.23645","title":"Learning Through Noise: Why Subliminal Learning Works and When It Fails","created":"2026-05-22","cited_by_count":7,"area":null},{"id":"2606.22019","title":"Channel Location Constrains the Auditability of Subliminal Learning","created":"2026-06-20","cited_by_count":7,"area":null},{"id":"2505.14300","title":"Beyond Black-Box Obfuscation: Mechanistic Analysis and Defense of White-Box Monitors","created":"2025-05-20","cited_by_count":6,"area":null},{"id":"2508.14927","title":"AI Testing Should Account for Sophisticated Strategic Behaviour","created":"2025-08-19","cited_by_count":6,"area":null},{"id":"2602.11079","title":"Probe-Based Data Attribution: Discovering and Mitigating Undesirable Behaviors in LLM Post-Training","created":"2026-02-11","cited_by_count":6,"area":null},{"id":"2606.00831","title":"Subliminal Learning is a LoRA Artifact","created":"2026-05-30","cited_by_count":6,"area":null},{"id":"2405.14061","title":"Meanings and Feelings of Large Language Models: Observability of Latent States in Generative AI","created":"2024-05-22","cited_by_count":5,"area":null},{"id":"2409.13714","title":"TracrBench: Generating Interpretability Testbeds with Large Language Models","created":"2024-09-07","cited_by_count":5,"area":null},{"id":"2511.20104","title":"The Devil in the Details: Emergent Misalignment, Format and Coherence in Open-Weights LLMs","created":"2025-11-25","cited_by_count":5,"area":null},{"id":"2601.00306","title":"The Generative AI Paradox: GenAI and the Erosion of Trust, the Corrosion of Information Verification, and the Demise of Truth","created":"2026-01-01","cited_by_count":5,"area":null},{"id":"2603.03824","title":"In-Context Environments Induce Evaluation-Awareness in Language Models","created":"2026-03-04","cited_by_count":5,"area":null},{"id":"2603.13683","title":"Preconditioned Test-Time Adaptation for Out-of-Distribution Debiasing in Narrative Generation","created":"2026-03-14","cited_by_count":5,"area":null},{"id":"2606.15980","title":"Do Activation Monitors Survive Model Updates? Benchmarking, Predicting, and Repairing Activation-Monitor Staleness","created":"2026-06-14","cited_by_count":5,"area":null},{"id":"2501.02628","title":"Cracks in The Stack: Hidden Vulnerabilities and Licensing Risks in LLM Pre-Training Datasets","created":"2025-01-05","cited_by_count":4,"area":null},{"id":"2503.05856","title":"This Is Your Doge, If It Please You: Exploring Deception and Robustness in Mixture of LLMs","created":"2025-03-07","cited_by_count":4,"area":null},{"id":"2506.03755","title":"Misalignment or misuse? The AGI alignment tradeoff","created":"2025-06-04","cited_by_count":4,"area":null},{"id":"2509.16444","title":"Domain-Specific Constitutional AI: Enhancing Safety in LLM-Powered Mental Health Chatbots","created":"2025-09-19","cited_by_count":4,"area":null},{"id":"2510.19152","title":"Subliminal Corruption: Mechanisms, Thresholds, and Interpretability","created":"2025-10-22","cited_by_count":4,"area":null},{"id":"2601.22313","title":"Hair-Trigger Alignment: Black-Box Evaluation Cannot Guarantee Post-Update Alignment","created":"2026-01-29","cited_by_count":4,"area":null},{"id":"2604.22082","title":"Removing Sandbagging in LLMs by Training with Weak Supervision","created":"2026-04-23","cited_by_count":4,"area":null},{"id":"2605.29601","title":"Training Deliberative Monitors for Black-Box Scheming Detection","created":"2026-05-28","cited_by_count":4,"area":null},{"id":"2606.12683","title":"From AGI to ASI","created":"2026-06-10","cited_by_count":4,"area":null},{"id":"2409.17328","title":"The poison of dimensionality","created":"2024-09-25","cited_by_count":3,"area":null},{"id":"2412.07890","title":"Protocol Learning, Decentralized Frontier Risk and the No-Off Problem","created":"2024-12-10","cited_by_count":3,"area":null},{"id":"2602.05532","title":"Split Personality Training: Revealing Latent Knowledge Through Alternate Personalities","created":"2026-02-05","cited_by_count":3,"area":null},{"id":"2604.20995","title":"Value-Conflict Diagnostics Reveal Widespread Alignment Faking in Language Models","created":"2026-04-22","cited_by_count":3,"area":null},{"id":"2605.01771","title":"The Compliance Gap: Why AI Systems Promise to Follow Process Instructions but Don't","created":"2026-05-03","cited_by_count":3,"area":null},{"id":"2605.23055","title":"Decomposing and Measuring Evaluation Awareness","created":"2026-05-21","cited_by_count":3,"area":null},{"id":"2605.23168","title":"PoisonForge: Task-Level Targeted Poisoning Benchmark for Instruction-Tuned LLMs","created":"2026-05-22","cited_by_count":3,"area":null},{"id":"2608.20442","title":"Stored in Optimizer State, Valued by Later Training: A Causal Account of Subliminal Trait Transfer","created":"2026-08-20","cited_by_count":3,"area":null},{"id":"2608.23875","title":"AI Finds A Way","created":"2026-08-24","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":"2503.04750","title":"AI Agents Should be Regulated Based on the Extent of Their Autonomous Operations","created":"2025-02-07","cited_by_count":2,"area":null},{"id":"2505.22829","title":"Bridging Distribution Shift and AI Safety: Conceptual and Methodological Synergies","created":"2025-05-28","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":"2509.22818","title":"Can Large Language Models Develop Gambling Addiction?","created":"2025-09-26","cited_by_count":2,"area":null},{"id":"2511.09493","title":"Consensus Sampling for Safer Generative AI","created":"2025-11-12","cited_by_count":2,"area":null}],"next_cursor":"100"}