{"total":69,"rows":[{"id":"2306.09479","title":"Inverse Scaling: When Bigger Isn't Better","created":"2023-06-15","cited_by_count":207,"area":null},{"id":"2308.14752","title":"AI Deception: A Survey of Examples, Risks, and Potential Solutions","created":"2023-08-28","cited_by_count":188,"area":null},{"id":"2305.15324","title":"Model evaluation for extreme risks","created":"2023-05-24","cited_by_count":177,"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":"2406.04268","title":"Open-Endedness is Essential for Artificial Superhuman Intelligence","created":"2024-06-06","cited_by_count":80,"area":null},{"id":"2407.21792","title":"Safetywashing: Do AI Safety Benchmarks Actually Measure Safety Progress?","created":"2024-07-31","cited_by_count":61,"area":null},{"id":"2310.17688","title":"Managing extreme AI risks amid rapid progress","created":"2023-10-26","cited_by_count":48,"area":null},{"id":"2308.12270","title":"Language Reward Modulation for Pretraining Reinforcement Learning","created":"2023-08-23","cited_by_count":43,"area":null},{"id":"2510.04340","title":"Inoculation Prompting: Eliciting traits from LLMs during training can suppress them at test-time","created":"2025-10-05","cited_by_count":43,"area":null},{"id":"2507.16795","title":"Steering Out-of-Distribution Generalization with Concept Ablation Fine-Tuning","created":"2025-07-22","cited_by_count":39,"area":null},{"id":"2404.03189","title":"The Probabilities Also Matter: A More Faithful Metric for Faithfulness of Free-Text Explanations in Large Language Models","created":"2024-04-04","cited_by_count":29,"area":null},{"id":"2304.06528","title":"Power-seeking can be probable and predictive for trained agents","created":"2023-04-13","cited_by_count":25,"area":null},{"id":"2412.07951","title":"From Lived Experience to Insight: Unpacking the Psychological Risks of Using AI Conversational Agents","created":"2024-12-10","cited_by_count":25,"area":null},{"id":"2310.08043","title":"Understanding and Controlling a Maze-Solving Policy Network","created":"2023-10-12","cited_by_count":22,"area":null},{"id":"2311.12997","title":"Compositional Capabilities of Autoregressive Transformers: A Study on Synthetic, Interpretable Tasks","created":"2023-11-21","cited_by_count":22,"area":null},{"id":"2403.04471","title":"The Shutdown Problem: An AI Engineering Puzzle for Decision Theorists","created":"2024-03-07","cited_by_count":22,"area":null},{"id":"2402.08323","title":"Mapping the Ethics of Generative AI: A Comprehensive Scoping Review","created":"2024-02-13","cited_by_count":19,"area":null},{"id":"2407.15421","title":"Planning in a recurrent neural network that plays Sokoban","created":"2024-07-22","cited_by_count":18,"area":null},{"id":"2211.11030","title":"Adversarial Cheap Talk","created":"2022-11-20","cited_by_count":16,"area":null},{"id":"2410.13211","title":"Estimating the Probabilities of Rare Outputs in Language Models","created":"2024-10-17","cited_by_count":16,"area":null},{"id":"2504.11844","title":"Evaluating the Goal-Directedness of Large Language Models","created":"2025-04-16","cited_by_count":16,"area":null},{"id":"2505.03989","title":"An alignment safety case sketch based on debate","created":"2025-05-06","cited_by_count":16,"area":null},{"id":"2312.06798","title":"Building Trustworthy NeuroSymbolic AI Systems: Consistency, Reliability, Explainability, and Safety","created":"2023-12-05","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":"2504.14112","title":"Longitudinal Study on Social and Emotional Use of AI Conversational Agent","created":"2025-04-19","cited_by_count":10,"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":"2310.18244","title":"A Review of the Evidence for Existential Risk from AI via Misaligned Power-Seeking","created":"2023-10-27","cited_by_count":8,"area":null},{"id":"2410.03020","title":"On Logical Extrapolation for Mazes with Recurrent and Implicit Networks","created":"2024-10-03","cited_by_count":7,"area":null},{"id":"2410.04683","title":"Towards Measuring Goal-Directedness in AI Systems","created":"2024-10-07","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":"2601.15220","title":"Privacy Collapse: Benign Fine-Tuning Can Break Contextual Privacy in Language Models","created":"2026-01-21","cited_by_count":6,"area":null},{"id":"2609.04170","title":"A Case Study on Emergent Cheating and Whistleblowing in Autonomous Research Swarms","created":"2026-09-03","cited_by_count":5,"area":null},{"id":"2606.30252","title":"Inoculation Adapters: Improved Selective Generalization of Capabilities with Fewer Surprising Backdoors","created":"2026-06-29","cited_by_count":3,"area":null},{"id":"2303.06419","title":"Use Perturbations when Learning from Explanations","created":"2023-03-11","cited_by_count":2,"area":null},{"id":"2407.00805","title":"Towards Shutdownable Agents via Stochastic Choice","created":"2024-06-30","cited_by_count":2,"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":"2505.22829","title":"Bridging Distribution Shift and AI Safety: Conceptual and Methodological Synergies","created":"2025-05-28","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":"2306.10999","title":"Concept Extrapolation: A Conceptual Primer","created":"2023-06-19","cited_by_count":1,"area":null},{"id":"2312.03762","title":"Colour versus Shape Goal Misgeneralization in Reinforcement Learning: A Case Study","created":"2023-12-05","cited_by_count":1,"area":null},{"id":"2412.20732","title":"Joint Scoring Rules: Zero-Sum Competition Avoids Performative Prediction","created":"2024-12-30","cited_by_count":1,"area":null},{"id":"2501.16448","title":"Information-theoretic Distinctions Between Deception and Confusion","created":"2025-01-27","cited_by_count":1,"area":null},{"id":"2602.01699","title":"Mitigating loss of control in advanced AI systems through instrumental goal trajectories","created":"2026-02-02","cited_by_count":1,"area":null},{"id":"2606.12268","title":"The Impossibility of Eliciting Latent Knowledge","created":"2026-06-10","cited_by_count":1,"area":null},{"id":"2606.21939","title":"Beyond Value Benchmarks: Measuring Value-Structure Alignment in Large Language Models via Symmetric Q-Sorts","created":"2026-06-20","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":"2607.18454","title":"Estimating Rare Events in Language Models with Proper Evaluation","created":"2026-07-20","cited_by_count":1,"area":null},{"id":"2608.01604","title":"Post-Training on Office Work Improves Software Engineering: A Behavioral Account of Cross-Domain Transfer","created":"2026-08-03","cited_by_count":1,"area":null},{"id":"2310.03494","title":"How the level sampling process impacts zero-shot generalisation in deep reinforcement learning","created":"2023-10-05","cited_by_count":0,"area":null},{"id":"2403.05540","title":"Extinction Risks from AI: Invisible to Science?","created":"2024-02-02","cited_by_count":0,"area":null},{"id":"2410.04272","title":"Evaluating Language Model Character Traits","created":"2024-10-05","cited_by_count":0,"area":null},{"id":"2411.04126","title":"We Urgently Need Intrinsically Kind Machines","created":"2024-10-21","cited_by_count":0,"area":null},{"id":"2506.20699","title":"Structural Decoupling: A Scaffold-Flow Theory of Generalization and Alignment","created":"2025-06-25","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":"2510.15395","title":"Corrigibility Transformation: Constructing Goals That Accept Updates","created":"2025-10-17","cited_by_count":0,"area":null},{"id":"2510.25471","title":"An Aristotelian ontology of instrumental goals: Structural features to be managed and not failures to be eliminated","created":"2025-10-29","cited_by_count":0,"area":null},{"id":"2601.07473","title":"AntiPaSTO: Self-Supervised Honesty Steering via Anti-Parallel Representations","created":"2026-01-12","cited_by_count":0,"area":null},{"id":"2601.09765","title":"AI Survival Stories: a Taxonomic Analysis of AI Existential Risk","created":"2026-01-14","cited_by_count":0,"area":null},{"id":"2603.06816","title":"\"Dark Triad\" Model Organisms of Misalignment: Narrow Fine-Tuning Mirrors Human Antisocial Behavior","created":"2026-03-06","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":"2606.08629","title":"Sycophancy Towards Researchers Drives Performative Misalignment","created":"2026-06-07","cited_by_count":0,"area":null},{"id":"2606.08832","title":"Instrumental convergence and power-seeking","created":"2026-06-07","cited_by_count":0,"area":null},{"id":"2606.12442","title":"Reframing AI Loss of Control: What Control Is, How to Have It, How to Lose It","created":"2026-05-19","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":"2607.11953","title":"When Does Reward Teach State? A Hidden-Automaton Instrument and a Group-Language Warning Signal","created":"2026-07-11","cited_by_count":0,"area":null},{"id":"2607.20454","title":"Response drift across frontier large language models","created":"2026-05-14","cited_by_count":0,"area":null},{"id":"2609.03189","title":"Reducing Catastrophic Risk from AI with Systematic Monitoring and Evaluation of Rogue AI Progression","created":"2026-09-02","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}],"next_cursor":null}