{"total":85,"rows":[{"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":"2506.19823","title":"Persona Features Control Emergent Misalignment","created":"2025-06-24","cited_by_count":86,"area":null},{"id":"2506.10805","title":"Detecting High-Stakes Interactions with Activation Probes","created":"2025-06-12","cited_by_count":53,"area":null},{"id":"2505.13763","title":"Language Models Are Capable of Metacognitive Monitoring and Control of Their Internal Activations","created":"2025-05-19","cited_by_count":41,"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":"2505.17120","title":"Self-Interpretability: LLMs Can Describe Complex Internal Processes that Drive Their Decisions","created":"2025-05-21","cited_by_count":25,"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":"2606.07682","title":"SWE-Marathon: Can Agents Autonomously Complete Ultra-Long-Horizon Software Work?","created":"2026-06-05","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":"2504.16728","title":"IRIS: Interactive Research Ideation System for Accelerating Scientific Discovery","created":"2025-04-23","cited_by_count":19,"area":null},{"id":"2507.12691","title":"Benchmarking Deception Probes via Black-to-White Performance Boosts","created":"2025-07-16","cited_by_count":19,"area":null},{"id":"2506.10922","title":"Robustly Improving LLM Fairness in Realistic Settings via Interpretability","created":"2025-06-12","cited_by_count":18,"area":null},{"id":"2512.19027","title":"Recontextualization Mitigates Specification Gaming without Modifying the Specification","created":"2025-12-22","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":"2605.12673","title":"Do Androids Dream of Breaking the Game? Systematically Auditing AI Agent Benchmarks with BenchJack","created":"2026-05-12","cited_by_count":14,"area":null},{"id":"2511.22662","title":"Difficulties with Evaluating a Deception Detector for AIs","created":"2025-11-27","cited_by_count":13,"area":null},{"id":"2601.21571","title":"Shaping capabilities with token-level data filtering","created":"2026-01-29","cited_by_count":13,"area":null},{"id":"2602.15515","title":"The Obfuscation Atlas: Mapping Where Honesty Emerges in RLVR with Deception Probes","created":"2026-02-17","cited_by_count":12,"area":null},{"id":"2506.10139","title":"Unsupervised Elicitation of Language Models","created":"2025-06-11","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":"2507.15886","title":"Combining Cost-Constrained Runtime Monitors for AI Safety","created":"2025-07-19","cited_by_count":10,"area":null},{"id":"2601.05752","title":"AutoMonitor-Bench: Evaluating the Reliability of LLM-Based Misbehavior Monitor","created":"2026-01-09","cited_by_count":10,"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":"2603.10011","title":"Gemma Needs Help: Investigating and Mitigating Emotional Instability in LLMs","created":"2026-02-17","cited_by_count":7,"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":"2511.16858","title":"Investigating Test Overfitting on SWE-bench","created":"2025-11-20","cited_by_count":6,"area":null},{"id":"2512.03399","title":"Full-Stack Alignment: Co-Aligning AI and Institutions with Thick Models of Value","created":"2025-12-03","cited_by_count":6,"area":null},{"id":"2512.16883","title":"AdaSearch: Balancing Parametric Knowledge and Search in Large Language Models via Reinforcement Learning","created":"2025-12-18","cited_by_count":6,"area":null},{"id":"2608.08888","title":"Full-bandwidth transformer","created":"2026-08-09","cited_by_count":5,"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":"2606.02211","title":"Consistency Training while Mitigating Obfuscation via Rate Matching","created":"2026-06-01","cited_by_count":4,"area":null},{"id":"2507.23330","title":"AI Must not be Fully Autonomous","created":"2025-07-31","cited_by_count":3,"area":null},{"id":"2604.11072","title":"Hodoscope: Unsupervised Monitoring for AI Misbehaviors","created":"2026-04-13","cited_by_count":3,"area":null},{"id":"2605.16198","title":"Formal Methods Meet LLMs: Auditing, Monitoring, and Intervention for Compliance of Advanced AI Systems","created":"2026-05-15","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":"2605.25052","title":"Faithfulness Metrics Don't Measure Faithfulness: A Meta-Evaluation with Ground Truth","created":"2026-05-24","cited_by_count":3,"area":null},{"id":"2607.14345","title":"Value Leakage: An LLM's Answers Are Silently Shaped by Its Own Values","created":"2026-07-15","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":"2510.10028","title":"Efficient Onboard Vision-Language Inference in UAV-Enabled Low-Altitude Economy Networks via LLM-Enhanced Optimization","created":"2025-10-11","cited_by_count":2,"area":null},{"id":"2510.21531","title":"Probe-based Fine-tuning for Reducing Toxicity","created":"2025-10-24","cited_by_count":2,"area":null},{"id":"2605.01643","title":"AI Alignment via Incentives and Correction","created":"2026-05-02","cited_by_count":2,"area":null},{"id":"2605.25252","title":"Quantifying Empirical Compute-Supervision Tradeoffs in RLVR","created":"2026-05-24","cited_by_count":2,"area":null},{"id":"2609.01595","title":"Mechanism Design for Alignment and Control","created":"2026-09-01","cited_by_count":2,"area":null},{"id":"2505.21570","title":"Beyond Explainability: The Case for AI Validation","created":"2025-05-27","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":"2603.11356","title":"Resolving Java Code Repository Issues with iSWE Agent","created":"2026-03-11","cited_by_count":1,"area":null},{"id":"2604.03968","title":"TraceGuard: Structured Multi-Dimensional Monitoring as a Collusion-Resistant Control Protocol","created":"2026-04-05","cited_by_count":1,"area":null},{"id":"2606.09931","title":"A Note on the Strategic Confinement Problem","created":"2026-06-07","cited_by_count":1,"area":null},{"id":"2606.26071","title":"Model Forensics: Investigating Whether Concerning Behavior Reflects Misalignment","created":"2026-06-24","cited_by_count":1,"area":null},{"id":"2607.01567","title":"Scaling Trends for Lie Detector Oversight in Preference Learning","created":"2026-07-02","cited_by_count":1,"area":null},{"id":"2608.03070","title":"AI Security Leaderboard: Methodology, Results and Minimal Standard","created":"2026-08-04","cited_by_count":1,"area":null},{"id":"2609.02852","title":"The Implications of Linguistic Illegibility for LLM Security","created":"2026-09-02","cited_by_count":1,"area":null},{"id":"2507.10590","title":"Repairing Language Model Pipelines by Meta Self-Refining Competing Constraints at Runtime","created":"2025-07-11","cited_by_count":0,"area":null},{"id":"2508.06017","title":"Position: Intelligent Coding Systems Should Write Programs with Justifications","created":"2025-08-08","cited_by_count":0,"area":null},{"id":"2510.11834","title":"Don't Walk the Line: Boundary Guidance for Filtered Generation","created":"2025-10-13","cited_by_count":0,"area":null},{"id":"2511.20736","title":"Large Language Models' Complicit Responses to Illicit Instructions across Socio-Legal Contexts","created":"2025-11-25","cited_by_count":0,"area":null},{"id":"2602.17676","title":"Epistemic Traps: Rational Misalignment Driven by Model Misspecification","created":"2026-01-27","cited_by_count":0,"area":null},{"id":"2602.20400","title":"Three Concrete Challenges and Two Hopes for the Safety of Unsupervised Elicitation","created":"2026-02-23","cited_by_count":0,"area":null},{"id":"2603.22017","title":"Domain Adapted Large Language Models for Additive Manufacturing","created":"2026-03-23","cited_by_count":0,"area":null},{"id":"2603.24037","title":"A$^3$: Towards Advertising Aesthetic Assessment","created":"2026-03-25","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":"2606.08629","title":"Sycophancy Towards Researchers Drives Performative Misalignment","created":"2026-06-07","cited_by_count":0,"area":null},{"id":"2606.10456","title":"The Distributed Detectability Band Against Marginal-Preserving Attacks","created":"2026-06-09","cited_by_count":0,"area":null},{"id":"2606.11445","title":"Forecasting Future Behavior as a Learning Task","created":"2026-06-09","cited_by_count":0,"area":null},{"id":"2606.25973","title":"Helpful or Harmful? Evaluating LLM-Assisted Vulnerability Patching via a Human Study","created":"2026-06-24","cited_by_count":0,"area":null},{"id":"2606.30219","title":"EvalSafetyGap: A Hybrid Survey and Conceptual Framework for LLM Evaluation-Safety Failures","created":"2026-06-29","cited_by_count":0,"area":null},{"id":"2607.02510","title":"Online Safety Monitoring for LLMs","created":"2026-07-02","cited_by_count":0,"area":null},{"id":"2607.20444","title":"Confidently Deceptive: On the Relationship Between Confidence and Deception in LLMs","created":"2026-05-12","cited_by_count":0,"area":null},{"id":"2607.26179","title":"Cognitive Convergence: Deep Similarities Between Large Language Models and Human Cognition","created":"2026-07-28","cited_by_count":0,"area":null},{"id":"2607.27557","title":"Skill Training with Corruption and Reconstruction Loop","created":"2026-07-30","cited_by_count":0,"area":null},{"id":"2608.14630","title":"Characterizing Rhetorical Misalignment in Decision-Making with Language Models","created":"2026-07-24","cited_by_count":0,"area":null},{"id":"2608.28099","title":"Speculative Probing: LLM Monitoring at Speculative-Decoding Cost","created":"2026-08-28","cited_by_count":0,"area":null},{"id":"2609.00904","title":"In-Context Neurofeedback: Can LLMs Control Their Internal Representations through Privileged Access?","created":"2026-09-01","cited_by_count":0,"area":null},{"id":"2609.07627","title":"Norms at a Price: Why RL-Based Alignment Can Promise Conditional Compliance at Best","created":"2026-09-07","cited_by_count":0,"area":null},{"id":"2609.20614","title":"Inference-Engine Fingerprinting Attacks are Practical: Exploring Model-Driven Environmental Discovery, Exploitation, and Escape","created":"2026-09-17","cited_by_count":0,"area":null},{"id":"2609.32061","title":"Contract monitoring: governing AI via separation of powers","created":"2026-09-25","cited_by_count":0,"area":null},{"id":"2609.36049","title":"Improving scalable oversight with co-trained monitors","created":"2026-09-28","cited_by_count":0,"area":null},{"id":"2609.36139","title":"Language Models Are \"Insecure\" Reporters","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":"2609.38262","title":"When Does Randomized Oversight Align AI Agents That Can Conceal?","created":"2026-09-29","cited_by_count":0,"area":null},{"id":"2610.09384","title":"The Persona Hierarchy Model: Understanding Contextual Generalization in Fine-Tuning LLMs","created":"2026-10-07","cited_by_count":0,"area":null},{"id":"2610.10064","title":"Comprehension Audits to Mitigate Risks from Automated AI Research","created":"2026-10-07","cited_by_count":0,"area":null},{"id":"2610.17370","title":"HarnessTTT: Learn to Optimize Harness at Test-Time for Scientific Discovery","created":"2026-10-12","cited_by_count":0,"area":null},{"id":"2610.18813","title":"Self-Evolving Agent Harness","created":"2026-10-13","cited_by_count":0,"area":null},{"id":"2610.20179","title":"Cross-Model In-Context Neurofeedback Reveals (Limited) Activation Control in LLMs","created":"2026-10-14","cited_by_count":0,"area":null}],"next_cursor":null}