{"total":95,"rows":[{"id":"2209.11895","title":"In-context Learning and Induction Heads","created":"2022-09-24","cited_by_count":964,"area":null},{"id":"2504.01848","title":"PaperBench: Evaluating AI's Ability to Replicate AI Research","created":"2025-04-02","cited_by_count":321,"area":null},{"id":"2303.00001","title":"Reward Design with Language Models","created":"2023-02-27","cited_by_count":261,"area":null},{"id":"2209.00626","title":"The Alignment Problem from a Deep Learning Perspective","created":"2022-08-30","cited_by_count":258,"area":null},{"id":"2306.12001","title":"An Overview of Catastrophic AI Risks","created":"2023-06-21","cited_by_count":222,"area":null},{"id":"2406.10162","title":"Sycophancy to Subterfuge: Investigating Reward-Tampering in Large Language Models","created":"2024-06-14","cited_by_count":178,"area":null},{"id":"2205.11275","title":"RL with KL penalties is better viewed as Bayesian inference","created":"2022-05-23","cited_by_count":135,"area":null},{"id":"2212.03363","title":"Few-Shot Preference Learning for Human-in-the-Loop RL","created":"2022-12-06","cited_by_count":87,"area":null},{"id":"2306.00186","title":"Factually Consistent Summarization via Reinforcement Learning with Textual Entailment Feedback","created":"2023-05-31","cited_by_count":72,"area":null},{"id":"2311.10766","title":"Value FULCRA: Mapping Large Language Models to the Multidimensional Spectrum of Basic Human Values","created":"2023-11-15","cited_by_count":50,"area":null},{"id":"2310.17688","title":"Managing extreme AI risks amid rapid progress","created":"2023-10-26","cited_by_count":48,"area":null},{"id":"2310.09144","title":"Goodhart's Law in Reinforcement Learning","created":"2023-10-13","cited_by_count":41,"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":"2502.12081","title":"Unhackable Temporal Rewarding for Scalable Video MLLMs","created":"2025-02-17","cited_by_count":33,"area":null},{"id":"2211.08714","title":"Reward Gaming in Conditional Text Generation","created":"2022-11-16","cited_by_count":30,"area":null},{"id":"2408.12578","title":"A Percolation Model of Emergence: Analyzing Transformers Trained on a Formal Language","created":"2024-08-22","cited_by_count":26,"area":null},{"id":"2303.16200","title":"Natural Selection Favors AIs over Humans","created":"2023-03-28","cited_by_count":24,"area":null},{"id":"2509.10147","title":"Virtual Agent Economies","created":"2025-09-12","cited_by_count":21,"area":null},{"id":"2405.19524","title":"AI Risk Management Should Incorporate Both Safety and Security","created":"2024-05-29","cited_by_count":17,"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":"2309.15257","title":"STARC: A General Framework For Quantifying Differences Between Reward Functions","created":"2023-09-26","cited_by_count":15,"area":null},{"id":"2210.12546","title":"Policy Optimization with Advantage Regularization for Long-Term Fairness in Decision Systems","created":"2022-10-22","cited_by_count":14,"area":null},{"id":"2210.11846","title":"Redefining Counterfactual Explanations for Reinforcement Learning: Overview, Challenges and Opportunities","created":"2022-10-21","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":"2506.01955","title":"Dual-Process Image Generation","created":"2025-06-02","cited_by_count":12,"area":null},{"id":"2503.05996","title":"Towards Improving Reward Design in RL: A Reward Alignment Metric for RL Practitioners","created":"2025-03-08","cited_by_count":10,"area":null},{"id":"2310.17769","title":"Social Contract AI: Aligning AI Assistants with Implicit Group Norms","created":"2023-10-26","cited_by_count":9,"area":null},{"id":"2404.03304","title":"Concept -- An Evaluation Protocol on Conversational Recommender Systems with System-centric and User-centric Factors","created":"2024-04-04","cited_by_count":9,"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":"2411.11767","title":"Drowning in Documents: Consequences of Scaling Reranker Inference","created":"2024-11-18","cited_by_count":8,"area":null},{"id":"2310.15288","title":"Active teacher selection for reward learning","created":"2023-10-23","cited_by_count":7,"area":null},{"id":"2405.17088","title":"Phase Transitions in the Output Distribution of Large Language Models","created":"2024-05-27","cited_by_count":7,"area":null},{"id":"2409.14399","title":"Beyond Persuasion: Towards Conversational Recommender System with Credible Explanations","created":"2024-09-22","cited_by_count":7,"area":null},{"id":"2403.02528","title":"DACO: Towards Application-Driven and Comprehensive Data Analysis via Code Generation","created":"2024-03-04","cited_by_count":6,"area":null},{"id":"2510.00931","title":"Making, not Taking, the Best of N","created":"2025-10-01","cited_by_count":6,"area":null},{"id":"2312.03881","title":"FoMo Rewards: Can we cast foundation models as reward functions?","created":"2023-12-06","cited_by_count":4,"area":null},{"id":"2503.04969","title":"Data-Efficient Learning from Human Interventions for Mobile Robots","created":"2025-03-06","cited_by_count":4,"area":null},{"id":"2412.03824","title":"Towards Data Governance of Frontier AI Models","created":"2024-12-05","cited_by_count":3,"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":"2603.19453","title":"Beyond Scalar Rewards: Dense Feedback for LLM Policy Synthesis in Sequential Social Dilemmas","created":"2026-03-19","cited_by_count":3,"area":null},{"id":"2608.23875","title":"AI Finds A Way","created":"2026-08-24","cited_by_count":3,"area":null},{"id":"2407.00805","title":"Towards Shutdownable Agents via Stochastic Choice","created":"2024-06-30","cited_by_count":2,"area":null},{"id":"2508.15442","title":"Mitigating Hallucinations in LM-Based TTS Models via Distribution Alignment Using GFlowNets","created":"2025-08-21","cited_by_count":2,"area":null},{"id":"2511.06148","title":"Large Language Models Develop Novel Social Biases Through Adaptive Exploration","created":"2025-11-08","cited_by_count":2,"area":null},{"id":"2603.24126","title":"Likelihood Hacking in Probabilistic Program Synthesis","created":"2026-03-25","cited_by_count":2,"area":null},{"id":"2605.18580","title":"When Outcome Looks Right But Discipline Fails: Trace-Based Evaluation Under Hidden Competitor State","created":"2026-05-18","cited_by_count":2,"area":null},{"id":"2605.25252","title":"Quantifying Empirical Compute-Supervision Tradeoffs in RLVR","created":"2026-05-24","cited_by_count":2,"area":null},{"id":"2605.28918","title":"When LLM Reward Design Fails: Diagnostic-Driven Refinement for Sparse Structured RL","created":"2026-05-27","cited_by_count":2,"area":null},{"id":"2607.07435","title":"RLVP: Penalize the Path, Reward the Outcome","created":"2026-07-08","cited_by_count":2,"area":null},{"id":"2304.12241","title":"Positive AI: Key Challenges in Designing Artificial Intelligence for Wellbeing","created":"2023-04-12","cited_by_count":1,"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":"2308.16364","title":"Strengthening the EU AI Act: Defining Key Terms on AI Manipulation","created":"2023-08-30","cited_by_count":1,"area":null},{"id":"2406.05086","title":"Robust Reward Design for Markov Decision Processes","created":"2024-06-07","cited_by_count":1,"area":null},{"id":"2509.15932","title":"The Alignment Bottleneck","created":"2025-09-19","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":"2603.00078","title":"Alignment Is Not Enough: A Relational Framework for Moral Standing in Human-AI Interaction","created":"2026-02-13","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":"2605.06529","title":"Market-Alignment Risk in Pricing Agents: Trace Diagnostics and Trace-Prior RL under Hidden Competitor State","created":"2026-05-07","cited_by_count":1,"area":null},{"id":"2606.03968","title":"QUBRIC: Co-Designing Queries and Rubrics for RL Beyond Verifiable Rewards","created":"2026-06-02","cited_by_count":1,"area":null},{"id":"2606.09931","title":"A Note on the Strategic Confinement Problem","created":"2026-06-07","cited_by_count":1,"area":null},{"id":"2606.11417","title":"Signed Compression Progress on a Sealed Audit is Goodhart-Resistant","created":"2026-06-09","cited_by_count":1,"area":null},{"id":"2608.04896","title":"When Shared Rollouts Fail in Defensive Driving Evaluation: A NAVSIM Score Basis Audit","created":"2026-08-05","cited_by_count":1,"area":null},{"id":"2609.00077","title":"Beneath the Diff: Diagnosing and Mitigating Algorithmic Mode Collapse in Code-Level Autonomous Research Loops","created":"2026-08-31","cited_by_count":1,"area":null},{"id":"2311.12004","title":"Risk-averse Batch Active Inverse Reward Design","created":"2023-11-20","cited_by_count":0,"area":null},{"id":"2312.08602","title":"Omega-Regular Decision Processes","created":"2023-12-14","cited_by_count":0,"area":null},{"id":"2403.15826","title":"Scaling Learning based Policy Optimization for Temporal Logic Tasks by Controller Network Dropout","created":"2024-03-23","cited_by_count":0,"area":null},{"id":"2503.17674","title":"MultiScale Contextual Bandits for Long Term Objectives","created":"2025-03-22","cited_by_count":0,"area":null},{"id":"2504.11250","title":"A Rollout-Based Algorithm and Reward Function for Resource Allocation in Business Processes","created":"2025-04-15","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":"2601.17577","title":"Status Hierarchies in Language Models","created":"2026-01-24","cited_by_count":0,"area":null},{"id":"2601.21523","title":"Explicit Credit Assignment through Local Rewards and Dependence Graphs in Multi-Agent Reinforcement Learning","created":"2026-01-29","cited_by_count":0,"area":null},{"id":"2602.18633","title":"DP-RFT: Learning to Generate Synthetic Text via Differentially Private Reinforcement Fine-Tuning","created":"2026-02-20","cited_by_count":0,"area":null},{"id":"2604.12500","title":"Safety Training Modulates Harmful Misalignment Under On-Policy RL, But Direction Depends on Environment Design","created":"2026-04-14","cited_by_count":0,"area":null},{"id":"2604.21103","title":"AI Governance under Political Turnover: The Alignment Surface of Compliance Design","created":"2026-04-22","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":"2605.16035","title":"Who Owns This Agent? Tracing AI Agents Back to Their Owners","created":"2026-05-15","cited_by_count":0,"area":null},{"id":"2605.24096","title":"The Time is Here for Just-in-Time Systems: Challenges and Opportunities","created":"2026-05-22","cited_by_count":0,"area":null},{"id":"2605.30719","title":"When are LLMs Sufficient Policy Optimizers for Sequential RL Tasks?","created":"2026-05-29","cited_by_count":0,"area":null},{"id":"2606.00414","title":"Auditing Near-Optimal Policies Can Be Exponentially Hard: Conditional Query Lower Bounds via Occupancy Rashomon Capacity","created":"2026-05-29","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":"2606.16914","title":"Greed Is Learned: Visible Incentives as Reward-Hacking Triggers","created":"2026-06-15","cited_by_count":0,"area":null},{"id":"2606.21413","title":"CAT-Translate: Building Compact Open-Source Models for Japanese-English Translation","created":"2026-06-19","cited_by_count":0,"area":null},{"id":"2607.07021","title":"Learning social norms enhances compatibility in dynamic human-AI coordination","created":"2026-07-08","cited_by_count":0,"area":null},{"id":"2607.08961","title":"NL-PAC: Specification Ambiguity and Certified Minimax Risk Floors in LLM-Mediated Supervision","created":"2026-07-09","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":"2607.25333","title":"Specula: Scaling formal specifications for autonomous model checking of system code","created":"2026-07-28","cited_by_count":0,"area":null},{"id":"2608.06422","title":"Sharding Prevents LLM Oversight Failures and Adversarial Exploitation","created":"2026-08-05","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":"2608.11560","title":"When Offline Evaluation Misleads: A Diagnostic Protocol for Reward and Policy Selection in Delayed-Feedback Contextual Bandits","created":"2026-08-12","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":"2609.31186","title":"Evolutionary Safety of Recursive Self-Improving AI: Taxonomy, Risk Discovery, and Evaluation","created":"2026-09-25","cited_by_count":0,"area":null},{"id":"2609.34688","title":"Unified Trajectory Matching Policy Optimization: Diverse T2I Generation and VLA Generalization","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":"2610.04364","title":"A Bird's-Eye View of Iterative Reward Design","created":"2026-10-03","cited_by_count":0,"area":null}],"next_cursor":null}