{"total":17,"rows":[{"id":"2507.01786","title":"Probing and Steering Evaluation Awareness of Language Models","created":"2025-07-02","cited_by_count":35,"area":null},{"id":"2603.12228","title":"Neural Thickets: Diverse Task Experts Are Dense Around Pretrained Weights","created":"2026-03-12","cited_by_count":28,"area":null},{"id":"2509.00591","title":"Probe-Rewrite-Evaluate: A Workflow for Reliable Benchmarks and Quantifying Evaluation Awareness","created":"2025-08-30","cited_by_count":9,"area":null},{"id":"2507.12872","title":"Manipulation Attacks by Misaligned AI: Risk Analysis and Safety Case Framework","created":"2025-07-17","cited_by_count":5,"area":null},{"id":"2604.17465","title":"Language models recognize dropout and Gaussian noise applied to their activations","created":"2026-04-19","cited_by_count":5,"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":"2609.01595","title":"Mechanism Design for Alignment and Control","created":"2026-09-01","cited_by_count":2,"area":null},{"id":"2504.03302","title":"Noise Augmented Fine Tuning for Mitigating Hallucinations in Large Language Models","created":"2025-04-04","cited_by_count":1,"area":null},{"id":"2509.26239","title":"Sandbagging in a Simple Survival Bandit Problem","created":"2025-09-30","cited_by_count":1,"area":null},{"id":"2602.07259","title":"Incentive-Aware AI Safety via Strategic Resource Allocation: A Stackelberg Security Games Perspective","created":"2026-02-06","cited_by_count":1,"area":null},{"id":"2604.25249","title":"Below-Chance Blindness: Prompted Underperformance in Small LLMs Produces Positional Bias Rather than Answer Avoidance","created":"2026-04-28","cited_by_count":1,"area":null},{"id":"2602.14529","title":"Disentangling Deception and Hallucination Failures in LLMs","created":"2026-02-16","cited_by_count":0,"area":null},{"id":"2604.26206","title":"Option-Order Randomisation Reveals a Distributional Position Attractor in Prompted Sandbagging","created":"2026-04-29","cited_by_count":0,"area":null},{"id":"2605.06327","title":"Measuring Evaluation-Context Divergence in Open-Weight LLMs: A Paired-Prompt Protocol with Pilot Evidence of Alignment-Pipeline-Specific Heterogeneity","created":"2026-05-07","cited_by_count":0,"area":null},{"id":"2609.06190","title":"One Perturbation Is Not Enough: Identifiability and Blind Baselines for Behavioral AI Evaluation","created":"2026-09-05","cited_by_count":0,"area":null},{"id":"2609.32530","title":"Activation Flow: Manufacturing Activations for Steering","created":"2026-09-26","cited_by_count":0,"area":null},{"id":"2610.13928","title":"AI Models Can Provably Hide Arbitrary Capabilities","created":"2026-10-09","cited_by_count":0,"area":null}],"next_cursor":null}