{"total":61,"rows":[{"id":"2209.00626","title":"The Alignment Problem from a Deep Learning Perspective","created":"2022-08-30","cited_by_count":258,"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":"2210.01790","title":"Goal Misgeneralization: Why Correct Specifications Aren't Enough For Correct Goals","created":"2022-10-04","cited_by_count":126,"area":null},{"id":"2404.00282","title":"Survey on Large Language Model-Enhanced Reinforcement Learning: Concept, Taxonomy, and Methods","created":"2024-03-30","cited_by_count":116,"area":null},{"id":"2306.00937","title":"STEVE-1: A Generative Model for Text-to-Behavior in Minecraft","created":"2023-06-01","cited_by_count":97,"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":"2304.00612","title":"Eight Things to Know about Large Language Models","created":"2023-04-02","cited_by_count":73,"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":"2410.04332","title":"Gradient Routing: Masking Gradients to Localize Computation in Neural Networks","created":"2024-10-06","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":"2306.08649","title":"OCAtari: Object-Centric Atari 2600 Reinforcement Learning Environments","created":"2023-06-14","cited_by_count":30,"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":"2310.08043","title":"Understanding and Controlling a Maze-Solving Policy Network","created":"2023-10-12","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":"2407.15421","title":"Planning in a recurrent neural network that plays Sokoban","created":"2024-07-22","cited_by_count":18,"area":null},{"id":"2302.12689","title":"GANterfactual-RL: Understanding Reinforcement Learning Agents' Strategies through Visual Counterfactual Explanations","created":"2023-02-24","cited_by_count":17,"area":null},{"id":"2308.10797","title":"Stabilizing Unsupervised Environment Design with a Learned Adversary","created":"2023-08-21","cited_by_count":17,"area":null},{"id":"2211.11030","title":"Adversarial Cheap Talk","created":"2022-11-20","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":"2306.02419","title":"Bad Habits: Policy Confounding and Out-of-Trajectory Generalization in RL","created":"2023-06-04","cited_by_count":10,"area":null},{"id":"2412.04758","title":"Measuring Goal-Directedness","created":"2024-12-06","cited_by_count":7,"area":null},{"id":"2402.12907","title":"Roadmap on Incentive Compatibility for AI Alignment and Governance in Sociotechnical Systems","created":"2024-02-20","cited_by_count":6,"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":"2603.10028","title":"How to Count AIs: Individuation and Liability for AI Agents","created":"2026-02-24","cited_by_count":5,"area":null},{"id":"2305.07888","title":"Consistency Regularization for Domain Generalization with Logit Attribution Matching","created":"2023-05-13","cited_by_count":4,"area":null},{"id":"2506.03755","title":"Misalignment or misuse? The AGI alignment tradeoff","created":"2025-06-04","cited_by_count":4,"area":null},{"id":"2510.21332","title":"Weak-to-Strong Generalization under Distribution Shifts","created":"2025-10-24","cited_by_count":4,"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":"2304.11104","title":"Approximate Shielding of Atari Agents for Safe Exploration","created":"2023-04-21","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":"2505.02313","title":"What Is AI Safety? What Do We Want It to Be?","created":"2025-05-05","cited_by_count":2,"area":null},{"id":"2508.19562","title":"Democracy-in-Silico: Institutional Design as Alignment in AI-Governed Polities","created":"2025-08-27","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":"2306.10999","title":"Concept Extrapolation: A Conceptual Primer","created":"2023-06-19","cited_by_count":1,"area":null},{"id":"2309.16166","title":"CoinRun: Solving Goal Misgeneralisation","created":"2023-09-28","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":"2410.07096","title":"Rejecting Hallucinated State Targets during Planning","created":"2024-10-09","cited_by_count":1,"area":null},{"id":"2504.15125","title":"Contemplative Artificial Intelligence","created":"2025-04-21","cited_by_count":1,"area":null},{"id":"2509.15932","title":"The Alignment Bottleneck","created":"2025-09-19","cited_by_count":1,"area":null},{"id":"2510.11235","title":"AI Alignment Strategies from a Risk Perspective: Independent Safety Mechanisms or Shared Failures?","created":"2025-10-13","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":"2306.13000","title":"Apolitical Intelligence? Auditing Delphi's responses on controversial political issues in the US","created":"2023-06-22","cited_by_count":0,"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":"2310.05871","title":"Dynamic value alignment through preference aggregation of multiple objectives","created":"2023-10-09","cited_by_count":0,"area":null},{"id":"2311.12004","title":"Risk-averse Batch Active Inverse Reward Design","created":"2023-11-20","cited_by_count":0,"area":null},{"id":"2402.09734","title":"Agents Need Not Know Their Purpose","created":"2024-02-15","cited_by_count":0,"area":null},{"id":"2503.13194","title":"A representational framework for learning and encoding structurally enriched trajectories in complex agent environments","created":"2025-03-17","cited_by_count":0,"area":null},{"id":"2505.20342","title":"Machine Theory of Mind and the Structure of Human Values","created":"2025-05-24","cited_by_count":0,"area":null},{"id":"2506.13790","title":"The NordDRG AI Benchmark for Large Language Models","created":"2025-06-11","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":"2601.07473","title":"AntiPaSTO: Self-Supervised Honesty Steering via Anti-Parallel Representations","created":"2026-01-12","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":"2604.24966","title":"Risk Reporting for Developers' Internal AI Model Use","created":"2026-04-27","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":"2607.03478","title":"Demonstrating Generalization Failures via Mixtures of Conditional Policies","created":"2026-07-03","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":"2608.08947","title":"Can Webcam Gaze Constrain Mesa-Objectives in Driving Models? An Instrument Precision Analysis","created":"2026-08-09","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":"2609.35400","title":"Structural Alignment for Reliable Industrial AI: Bridging Physical Reality, Data, Models, and Human Intent","created":"2026-09-28","cited_by_count":0,"area":null},{"id":"2610.04975","title":"Runtime Authorization of Self-Generated Subgoals in Long-Horizon Tool-Using AI Agents","created":"2026-10-04","cited_by_count":0,"area":null}],"next_cursor":null}