{"total":81,"rows":[{"id":"2504.01848","title":"PaperBench: Evaluating AI's Ability to Replicate AI Research","created":"2025-04-02","cited_by_count":321,"area":null},{"id":"2412.04984","title":"Frontier Models are Capable of In-context Scheming","created":"2024-12-06","cited_by_count":287,"area":null},{"id":"2410.13787","title":"Looking Inward: Language Models Can Learn About Themselves by Introspection","created":"2024-10-17","cited_by_count":113,"area":null},{"id":"2502.06559","title":"Can We Trust AI Benchmarks? An Interdisciplinary Review of Current Issues in AI Evaluation","created":"2025-02-10","cited_by_count":60,"area":null},{"id":"2410.21514","title":"Sabotage Evaluations for Frontier Models","created":"2024-10-28","cited_by_count":52,"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":"2505.01420","title":"Evaluating Frontier Models for Stealth and Situational Awareness","created":"2025-05-02","cited_by_count":37,"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":"2411.03336","title":"Towards evaluations-based safety cases for AI scheming","created":"2024-10-29","cited_by_count":33,"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":"2507.12691","title":"Benchmarking Deception Probes via Black-to-White Performance Boosts","created":"2025-07-16","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":"2602.11865","title":"Intelligent AI Delegation","created":"2026-02-12","cited_by_count":18,"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":"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":"2512.24661","title":"Do Large Language Models Know What They Are Capable Of?","created":"2025-12-31","cited_by_count":10,"area":null},{"id":"2511.17408","title":"The Impact of Off-Policy Training Data on Probe Generalisation","created":"2025-11-21","cited_by_count":9,"area":null},{"id":"2502.06470","title":"A Survey of Theory of Mind in Large Language Models: Evaluations, Representations, and Safety Risks","created":"2025-02-10","cited_by_count":8,"area":null},{"id":"2503.04744","title":"Safety Cases: A Scalable Approach to Frontier AI Safety","created":"2025-02-05","cited_by_count":8,"area":null},{"id":"2506.23706","title":"Attestable Audits: Verifiable AI Safety Benchmarks Using Trusted Execution Environments","created":"2025-06-30","cited_by_count":8,"area":null},{"id":"2510.08211","title":"LLMs Deceive Unintentionally: Emergent Misalignment in Dishonesty from Misaligned Samples to Biased Human-AI Interactions","created":"2025-10-09","cited_by_count":8,"area":null},{"id":"2602.23163","title":"A Decision-Theoretic Formalisation of Steganography With Applications to LLM Monitoring","created":"2026-02-26","cited_by_count":8,"area":null},{"id":"2504.20084","title":"AI Awareness","created":"2025-04-25","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":"2605.13329","title":"Tracing Persona Vectors Through LLM Pretraining","created":"2026-05-13","cited_by_count":7,"area":null},{"id":"2510.24626","title":"Relative Scaling Laws for LLMs","created":"2025-10-28","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":"2603.03824","title":"In-Context Environments Induce Evaluation-Awareness in Language Models","created":"2026-03-04","cited_by_count":5,"area":null},{"id":"2411.12820","title":"Declare and Justify: Explicit assumptions in AI evaluations are necessary for effective regulation","created":"2024-11-19","cited_by_count":4,"area":null},{"id":"2412.08653","title":"What AI evaluations for preventing catastrophic risks can and cannot do","created":"2024-11-26","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":"2603.26676","title":"Evaluating Human-AI Safety: A Framework for Measuring Harmful Capability Uplift","created":"2026-03-06","cited_by_count":3,"area":null},{"id":"2604.09104","title":"Scheming in the wild: detecting real-world AI scheming incidents with open-source intelligence","created":"2026-04-10","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":"2606.29604","title":"Mechanistically Eliciting Latent Behaviors in Language Models","created":"2026-06-28","cited_by_count":3,"area":null},{"id":"2602.05656","title":"Alignment Verifiability in Large Language Models: Normative Indistinguishability under Behavioral Evaluation","created":"2026-02-05","cited_by_count":2,"area":null},{"id":"2607.20436","title":"Routing Subspaces: Auditing Evaluation-to-Deployment Mismatch in Fine-Tuned Language Models","created":"2026-05-11","cited_by_count":2,"area":null},{"id":"2505.07846","title":"Winning at All Cost: A Small Environment for Eliciting Specification Gaming Behaviors in Large Language Models","created":"2025-05-07","cited_by_count":1,"area":null},{"id":"2604.17663","title":"ATLAS: Constitution-Conditioned Latent Geometry and Redistribution Across Language Models and Neural Perturbation Data","created":"2026-04-19","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":"2606.04413","title":"(Mis)generalization of Helpful-only Fine-tuning","created":"2026-06-03","cited_by_count":1,"area":null},{"id":"2606.06286","title":"LLMs Can Leak Training Data But Do They Want To? A Propensity-Aware Evaluation of Memorization in LLMs","created":"2026-06-04","cited_by_count":1,"area":null},{"id":"2607.14399","title":"Instrument Effects in Language-Model Honesty Evaluation: An Auditable Single-System Demonstration","created":"2026-07-15","cited_by_count":1,"area":null},{"id":"2608.05086","title":"Item Response Theory for AI Safety","created":"2026-08-05","cited_by_count":1,"area":null},{"id":"2608.29458","title":"Reference-Grafting Matches Fine-Tuning at Eliciting Sandbagged Capabilities","created":"2026-08-29","cited_by_count":1,"area":null},{"id":"2608.29461","title":"A Causal Model for Locating and Unlocking Sandbagging in Model Organisms","created":"2026-08-29","cited_by_count":1,"area":null},{"id":"2506.15735","title":"ContextBench: Modifying Contexts for Targeted Latent Activation","created":"2025-06-15","cited_by_count":0,"area":null},{"id":"2506.22977","title":"On the Generalizability of \"Competition of Mechanisms: Tracing How Language Models Handle Facts and Counterfactuals\"","created":"2025-06-28","cited_by_count":0,"area":null},{"id":"2510.02840","title":"Take Goodhart Seriously: Principled Limit on General-Purpose AI Optimization","created":"2025-10-03","cited_by_count":0,"area":null},{"id":"2602.08449","title":"When Evaluation Becomes a Side Channel: Regime Leakage and Structural Mitigations for Alignment Assessment","created":"2026-02-09","cited_by_count":0,"area":null},{"id":"2602.14529","title":"Disentangling Deception and Hallucination Failures in LLMs","created":"2026-02-16","cited_by_count":0,"area":null},{"id":"2603.14672","title":"Seamless Deception: Larger Language Models Are Better Knowledge Concealers","created":"2026-03-15","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":"2604.13301","title":"Honeypot Protocol","created":"2026-04-14","cited_by_count":0,"area":null},{"id":"2604.24966","title":"Risk Reporting for Developers' Internal AI Model Use","created":"2026-04-27","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":"2604.27249","title":"Instruction Complexity Induces Positional Collapse in Adversarial LLM Evaluation","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":"2605.10575","title":"Acceptance Cards:A Four-Diagnostic Standard for Safe Fine-Tuning Defense Claims","created":"2026-05-11","cited_by_count":0,"area":null},{"id":"2605.10601","title":"The Open-Box Fallacy: Why AI Deployment Needs a Calibrated Verification Regime","created":"2026-05-11","cited_by_count":0,"area":null},{"id":"2605.30916","title":"Welfare, Improvability, and Variance: A Principal-Agent Approach to Optimal Benchmark Item Aggregation","created":"2026-05-29","cited_by_count":0,"area":null},{"id":"2606.07631","title":"Trait-space Monitoring for Emergent Misalignment During Supervised Finetuning","created":"2026-05-31","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":"2606.28863","title":"Defeat Devices in AI Systems","created":"2026-06-27","cited_by_count":0,"area":null},{"id":"2607.24758","title":"Do Models Fake Alignment Without Clear Consequences?","created":"2026-05-28","cited_by_count":0,"area":null},{"id":"2607.24769","title":"LLM Scheming Inversely Scales with Pretraining Language Coverage","created":"2026-06-09","cited_by_count":0,"area":null},{"id":"2608.13329","title":"A Probe Direction Is a Property of Its Prompt","created":"2026-08-13","cited_by_count":0,"area":null},{"id":"2608.13840","title":"ASSERT: A Measurement Pipeline for GenAI Audits","created":"2026-08-14","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":"2609.06190","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":"2609.07162","title":"The Oversight Gap: What LLM Safety Monitors Miss, and Why It Is Not Capability","created":"2026-09-07","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":"2609.20408","title":"Xeno-Interpretability: Investigating the Alien Minds of LLMs","created":"2026-09-17","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":"2609.35409","title":"AwarenessBench: Assessing Cognitive Capabilities of Language Models","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":"2609.39807","title":"Stress-Testing LLM Lie Detectors: Role-Play Failures and Spurious Correlations","created":"2026-09-30","cited_by_count":0,"area":null},{"id":"2610.06174","title":"Anosognosia in LLMs: Probing Self-Awareness of Quantized Computational Substrate","created":"2026-10-05","cited_by_count":0,"area":null},{"id":"2610.09371","title":"The Confidence Game: Strategic Miscalibration in Human-AI Delegation","created":"2026-10-07","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},{"id":"2610.16043","title":"Beyond the greenwash: do LLMs' ecologically sound decisions hold up under pressure?","created":"2026-10-12","cited_by_count":0,"area":null}],"next_cursor":null}