{"total":80,"rows":[{"id":"2210.10760","title":"Scaling Laws for Reward Model Overoptimization","created":"2022-10-19","cited_by_count":1095,"area":"alignment"},{"id":"2307.15217","title":"Open Problems and Fundamental Limitations of Reinforcement Learning from Human Feedback","created":"2023-07-27","cited_by_count":759,"area":"alignment"},{"id":"2201.03544","title":"The Effects of Reward Misspecification: Mapping and Mitigating Misaligned Models","created":"2022-01-10","cited_by_count":328,"area":"alignment"},{"id":"2310.03716","title":"A Long Way to Go: Investigating Length Correlations in RLHF","created":"2023-10-05","cited_by_count":291,"area":"alignment"},{"id":"2209.00626","title":"The Alignment Problem from a Deep Learning Perspective","created":"2022-08-30","cited_by_count":258,"area":null},{"id":"2310.02743","title":"Reward Model Ensembles Help Mitigate Overoptimization","created":"2023-10-04","cited_by_count":231,"area":"alignment"},{"id":"2209.13085","title":"Defining and Characterizing Reward Hacking","created":"2022-09-27","cited_by_count":203,"area":"alignment"},{"id":"2401.12187","title":"WARM: On the Benefits of Weight Averaged Reward Models","created":"2024-01-22","cited_by_count":147,"area":"alignment"},{"id":"2312.08358","title":"Distributional Preference Learning: Understanding and Accounting for Hidden Context in RLHF","created":"2023-12-13","cited_by_count":133,"area":"alignment"},{"id":"2105.14111","title":"Goal Misgeneralization in Deep Reinforcement Learning","created":"2021-05-28","cited_by_count":123,"area":null},{"id":"2408.03943","title":"Building Machines that Learn and Think with People","created":"2024-07-22","cited_by_count":73,"area":null},{"id":"2408.16984","title":"Beyond Preferences in AI Alignment","created":"2024-08-30","cited_by_count":49,"area":"alignment"},{"id":"2310.17688","title":"Managing extreme AI risks amid rapid progress","created":"2023-10-26","cited_by_count":48,"area":null},{"id":"2405.19107","title":"Offline Regularised Reinforcement Learning for Large Language Models Alignment","created":"2024-05-29","cited_by_count":48,"area":"alignment"},{"id":"2403.03744","title":"MedSafetyBench: Evaluating and Improving the Medical Safety of Large Language Models","created":"2024-03-06","cited_by_count":44,"area":null},{"id":"2403.10854","title":"A Comprehensive Study of Multimodal Large Language Models for Image Quality Assessment","created":"2024-03-16","cited_by_count":43,"area":"mllm"},{"id":"2310.09144","title":"Goodhart's Law in Reinforcement Learning","created":"2023-10-13","cited_by_count":41,"area":null},{"id":"2410.05584","title":"Rethinking Reward Model Evaluation: Are We Barking up the Wrong Tree?","created":"2024-10-08","cited_by_count":31,"area":"lr"},{"id":"2204.12993","title":"Counterfactual harm","created":"2022-04-27","cited_by_count":29,"area":null},{"id":"2407.14503","title":"Catastrophic Goodhart: regularizing RLHF with KL divergence does not mitigate heavy-tailed reward misspecification","created":"2024-07-19","cited_by_count":23,"area":"alignment"},{"id":"2301.03652","title":"On The Fragility of Learned Reward Functions","created":"2023-01-09","cited_by_count":21,"area":"alignment"},{"id":"2403.04204","title":"On the Essence and Prospect: An Investigation of Alignment Approaches for Big Models","created":"2024-03-07","cited_by_count":21,"area":"alignment"},{"id":"2509.10147","title":"Virtual Agent Economies","created":"2025-09-12","cited_by_count":21,"area":null},{"id":"2309.15237","title":"User Experience Design Professionals' Perceptions of Generative Artificial Intelligence","created":"2023-09-26","cited_by_count":16,"area":null},{"id":"2309.15257","title":"STARC: A General Framework For Quantifying Differences Between Reward Functions","created":"2023-09-26","cited_by_count":15,"area":null},{"id":"2502.05454","title":"Temporal Representation Alignment: Successor Features Enable Emergent Compositionality in Robot Instruction Following","created":"2025-02-08","cited_by_count":14,"area":null},{"id":"2109.00484","title":"Impossibility Results in AI: A Survey","created":"2021-09-01","cited_by_count":13,"area":null},{"id":"2304.00416","title":"Towards Healthy AI: Large Language Models Need Therapists Too","created":"2023-04-02","cited_by_count":13,"area":null},{"id":"2401.00298","title":"Principal-Agent Reward Shaping in MDPs","created":"2023-12-30","cited_by_count":13,"area":null},{"id":"2408.05284","title":"Can a Bayesian Oracle Prevent Harm from an Agent?","created":"2024-08-09","cited_by_count":13,"area":null},{"id":"2411.02623","title":"Learning to Assist Humans without Inferring Rewards","created":"2024-11-04","cited_by_count":13,"area":"deeprl"},{"id":"2412.08812","title":"Test-Time Alignment via Hypothesis Reweighting","created":"2024-12-11","cited_by_count":11,"area":"alignment"},{"id":"2404.04932","title":"Towards Understanding the Influence of Reward Margin on Preference Model Performance","created":"2024-04-07","cited_by_count":9,"area":"alignment"},{"id":"2308.02435","title":"Designing Fiduciary Artificial Intelligence","created":"2023-07-27","cited_by_count":8,"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":"2503.00069","title":"Societal Alignment Frameworks Can Improve LLM Alignment","created":"2025-02-27","cited_by_count":8,"area":"alignment"},{"id":"2310.02263","title":"Automatic Pair Construction for Contrastive Post-training","created":"2023-10-03","cited_by_count":7,"area":null},{"id":"2312.01818","title":"Hybrid Approaches for Moral Value Alignment in AI Agents: a Manifesto","created":"2023-12-04","cited_by_count":7,"area":"agents"},{"id":"2408.17198","title":"Towards Symbolic XAI -- Explanation Through Human Understandable Logical Relationships Between Features","created":"2024-08-30","cited_by_count":7,"area":null},{"id":"2308.15605","title":"Benchmarks for Detecting Measurement Tampering","created":"2023-08-29","cited_by_count":6,"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":"2403.00188","title":"Impact of Decentralized Learning on Player Utilities in Stackelberg Games","created":"2024-02-29","cited_by_count":5,"area":null},{"id":"2110.05702","title":"Auditing Robot Learning for Safety and Compliance during Deployment","created":"2021-10-12","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":"2506.17846","title":"Out of Control -- Why Alignment Needs Formal Control Theory (and an Alignment Control Stack)","created":"2025-06-21","cited_by_count":3,"area":null},{"id":"2509.04445","title":"Towards Cognitively-Faithful Decision-Making Models to Improve AI Alignment","created":"2025-09-04","cited_by_count":3,"area":null},{"id":"2602.14252","title":"GRAIL: Goal Recognition Alignment through Imitation Learning","created":"2026-02-15","cited_by_count":3,"area":"offlinerl"},{"id":"2410.06213","title":"RL, but don't do anything I wouldn't do","created":"2024-10-08","cited_by_count":2,"area":"deeprl"},{"id":"2410.19219","title":"Robot Behavior Personalization from Sparse User Feedback","created":"2024-10-25","cited_by_count":2,"area":null},{"id":"2503.07341","title":"The Economics of p(doom): Scenarios of Existential Risk and Economic Growth in the Age of Transformative AI","created":"2025-03-10","cited_by_count":2,"area":null},{"id":"2505.20120","title":"Agents Require Metacognitive and Strategic Reasoning to Succeed in the Coming Labor Markets","created":"2025-05-26","cited_by_count":2,"area":null},{"id":"2505.23445","title":"The Strong, Weak and Benign Goodhart's law. An independence-free and paradigm-agnostic formalisation","created":"2025-05-29","cited_by_count":2,"area":null},{"id":"2308.01525","title":"VisAlign: Dataset for Measuring the Degree of Alignment between AI and Humans in Visual Perception","created":"2023-08-03","cited_by_count":1,"area":null},{"id":"2409.13919","title":"Measuring Error Alignment for Decision-Making Systems","created":"2024-09-20","cited_by_count":1,"area":"alignment"},{"id":"2412.00033","title":"Can an AI Agent Safely Run a Government? Existence of Probably Approximately Aligned Policies","created":"2024-11-21","cited_by_count":1,"area":null},{"id":"2412.16475","title":"When Can Proxies Improve the Sample Complexity of Preference Learning?","created":"2024-12-21","cited_by_count":1,"area":"alignment"},{"id":"2507.03068","title":"Mitigating Goal Misgeneralization via Minimax Regret","created":"2025-07-03","cited_by_count":1,"area":"deeprl"},{"id":"2508.00159","title":"Model-Based Soft Maximization of Suitable Metrics of Long-Term Human Power","created":"2025-07-31","cited_by_count":1,"area":null},{"id":"2510.16368","title":"The Burden of Interactive Alignment with Inconsistent Preferences","created":"2025-10-18","cited_by_count":1,"area":null},{"id":"2602.21556","title":"Power and Limitations of Aggregation in Compound AI Systems","created":"2026-02-25","cited_by_count":1,"area":null},{"id":"2603.15017","title":"Consequentialist Objectives and Catastrophe","created":"2026-03-16","cited_by_count":1,"area":null},{"id":"2605.18721","title":"General Preference Reinforcement Learning","created":"2026-05-18","cited_by_count":1,"area":"alignment"},{"id":"2606.23597","title":"Against Proxy Optimization","created":"2026-06-22","cited_by_count":1,"area":null},{"id":"2606.29657","title":"Safety from Honesty in a Disinterested AI Predictor","created":"2026-06-28","cited_by_count":1,"area":null},{"id":"2402.09734","title":"Agents Need Not Know Their Purpose","created":"2024-02-15","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":"2502.07790","title":"Can Generative AI be Egalitarian?","created":"2025-01-20","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":"2602.17676","title":"Epistemic Traps: Rational Misalignment Driven by Model Misspecification","created":"2026-01-27","cited_by_count":0,"area":null},{"id":"2603.13244","title":"Agentic AI, Retrieval-Augmented Generation, and the Institutional Turn: Legal Architectures and Financial Governance in the Age of Distributional AGI","created":"2026-02-20","cited_by_count":0,"area":"agents"},{"id":"2604.04182","title":"Comparative reversal learning reveals rigid adaptation in LLMs under non-stationary uncertainty","created":"2026-04-05","cited_by_count":0,"area":null},{"id":"2604.04237","title":"Pedagogical Safety in Educational Reinforcement Learning: Formalizing and Detecting Reward Hacking in AI Tutoring Systems","created":"2026-04-05","cited_by_count":0,"area":"alignment"},{"id":"2606.16914","title":"Greed Is Learned: Visible Incentives as Reward-Hacking Triggers","created":"2026-06-15","cited_by_count":0,"area":null},{"id":"2607.22305","title":"A Roadmap to Impactful Pluralistic Alignment Research","created":"2026-07-24","cited_by_count":0,"area":"alignment"},{"id":"2607.28881","title":"Fragility of Value under Imperfect Alignment","created":"2026-07-30","cited_by_count":0,"area":"alignment"},{"id":"2608.08240","title":"A Fair Objective for Human-Empowerment-Preserving AI: Desiderata, Design, and Likely Behavioral Consequences","created":"2026-08-08","cited_by_count":0,"area":null},{"id":"2608.18351","title":"Task-Conditioned Least-Privilege Learning for Executable Terminal and MCP Agents","created":"2026-08-18","cited_by_count":0,"area":"agents"},{"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":"2609.35677","title":"Verifier Errors in RLVR: Reward Hacking, Limits of Feedback, and Selective Control","created":"2026-09-28","cited_by_count":0,"area":"alignment"},{"id":"2610.17062","title":"Gradient Routing Localizes and Removes Unintended Behaviors in RL","created":"2026-10-12","cited_by_count":0,"area":"alignment"}],"next_cursor":null}