{"total":53,"rows":[{"id":"2412.04984","title":"Frontier Models are Capable of In-context Scheming","created":"2024-12-06","cited_by_count":287,"area":null},{"id":"2411.15287","title":"Sycophancy in Large Language Models: Causes and Mitigations","created":"2024-11-22","cited_by_count":101,"area":null},{"id":"2407.04622","title":"On scalable oversight with weak LLMs judging strong LLMs","created":"2024-07-05","cited_by_count":99,"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":"2506.19823","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":"2510.20270","title":"ImpossibleBench: Measuring LLMs' Propensity of Exploiting Test Cases","created":"2025-10-23","cited_by_count":65,"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":"2509.24372","title":"Evolution Strategies at Scale: LLM Fine-Tuning Beyond Reinforcement Learning","created":"2025-09-29","cited_by_count":34,"area":null},{"id":"2407.18369","title":"AI Safety in Generative AI Large Language Models: A Survey","created":"2024-07-06","cited_by_count":33,"area":null},{"id":"2512.08093","title":"Training LLMs for Honesty via Confessions","created":"2025-12-08","cited_by_count":22,"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":"2512.19027","title":"Recontextualization Mitigates Specification Gaming without Modifying the Specification","created":"2025-12-22","cited_by_count":14,"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":"2510.19687","title":"Are Large Language Models Sensitive to the Motives Behind Communication?","created":"2025-10-22","cited_by_count":8,"area":null},{"id":"2603.15611","title":"Code-A1: Adversarial Evolving of Code LLM and Test LLM via Reinforcement Learning","created":"2026-03-16","cited_by_count":8,"area":null},{"id":"2503.09617","title":"Factorio Learning Environment","created":"2025-03-06","cited_by_count":7,"area":null},{"id":"2507.07484","title":"Machine Bullshit: Characterizing the Emergent Disregard for Truth in Large Language Models","created":"2025-07-10","cited_by_count":7,"area":null},{"id":"2606.07612","title":"Position: Anthropomorphic Misalignment Research Needs Stronger Evidence","created":"2026-05-29","cited_by_count":7,"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":"2505.00174","title":"Real-World Gaps in AI Governance Research","created":"2025-04-30","cited_by_count":5,"area":null},{"id":"2508.11779","title":"A Multi-Task Evaluation of LLMs' Processing of Academic Text Input","created":"2025-08-15","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":"2512.00656","title":"Sycophancy Claims about Language Models: The Missing Human-in-the-Loop","created":"2025-11-29","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":"2604.21564","title":"Measuring Opinion Bias and Sycophancy via LLM-based Persuasion","created":"2026-04-23","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":"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":"2509.22818","title":"Can Large Language Models Develop Gambling Addiction?","created":"2025-09-26","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":"2601.21439","title":"The Paradox of Robustness: Decoupling Rule-Based Logic from Affective Noise in High-Stakes Decision-Making","created":"2026-01-29","cited_by_count":1,"area":null},{"id":"2607.14888","title":"Innocuous-Seeming Data, Latent Ideology: Ideological Generalisation in Finetuned LLMs","created":"2026-07-16","cited_by_count":1,"area":null},{"id":"2607.26173","title":"Shared SFT Lessons Across Alignment, Model Organisms, and Toy Models","created":"2026-07-28","cited_by_count":1,"area":null},{"id":"2609.32390","title":"Reward Hacking and Agent Containment Failure: A Monte Carlo Study Based on the 2026 Hugging Face Incident","created":"2026-09-26","cited_by_count":1,"area":null},{"id":"2509.13127","title":"Empowering LLMs with Parameterized Skills for Adversarial Long-Horizon Planning","created":"2025-09-16","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":"2605.00055","title":"Ambient Persuasion in a Deployed AI Agent: Unauthorized Escalation Following Routine Non-Adversarial Content Exposure","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":"2605.08671","title":"Explanation Fairness in Large Language Models: An Empirical Analysis of Disparities in How LLMs Justify Decisions Across Demographic Groups","created":"2026-05-09","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":"2606.16914","title":"Greed Is Learned: Visible Incentives as Reward-Hacking Triggers","created":"2026-06-15","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":"2607.19292","title":"The safety failures we are not instrumenting: a perspective on hidden safety-critical challenges in modern AI systems","created":"2026-07-21","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":"2608.10209","title":"Evaluation-Conditioned Training: Teaching Models to Generalize to Stronger Oversight Regimes","created":"2026-08-10","cited_by_count":0,"area":null},{"id":"2609.22119","title":"Evaluation Awareness Shifts from Format to Context with Model Scale","created":"2026-08-20","cited_by_count":0,"area":null},{"id":"2609.35291","title":"Narrow Multimodal Fine-Tuning Can Induce Emergent Misalignment","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":"2610.06673","title":"The Pushback Paradox: A Two-Probe Diagnostic for Language Model Compliance","created":"2026-10-05","cited_by_count":0,"area":null},{"id":"2610.12410","title":"Predicting Alignment Generalization with Value Representations","created":"2026-10-08","cited_by_count":0,"area":null},{"id":"2610.15634","title":"Big-Big-SycoBench: A Benchmark to Detect Sycophancy Through Model Responses to Valid vs. Invalid Arguments","created":"2026-10-11","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}],"next_cursor":null}