{"total":74,"rows":[{"id":"1811.07871","title":"Scalable agent alignment via reward modeling: a research direction","created":"2018-11-19","cited_by_count":447,"area":"alignment"},{"id":"2109.13916","title":"Unsolved Problems in ML Safety","created":"2021-09-28","cited_by_count":292,"area":null},{"id":"2110.06674","title":"Truthful AI: Developing and governing AI that does not lie","created":"2021-10-13","cited_by_count":113,"area":null},{"id":"2207.07411","title":"Plex: Towards Reliability using Pretrained Large Model Extensions","created":"2022-07-15","cited_by_count":102,"area":null},{"id":"2107.06857","title":"Scalable Evaluation of Multi-Agent Reinforcement Learning with Melting Pot","created":"2021-07-14","cited_by_count":99,"area":null},{"id":"2211.13746","title":"Melting Pot 2.0","created":"2022-11-24","cited_by_count":40,"area":null},{"id":"2105.05424","title":"Transitioning to human interaction with AI systems: New challenges and opportunities for HCI professionals to enable human-centered AI","created":"2021-05-12","cited_by_count":38,"area":null},{"id":"2201.00012","title":"MORAL: Aligning AI with Human Norms through Multi-Objective Reinforced Active Learning","created":"2021-12-30","cited_by_count":25,"area":"alignment"},{"id":"2310.03659","title":"Balancing Autonomy and Alignment: A Multi-Dimensional Taxonomy for Autonomous LLM-powered Multi-Agent Architectures","created":"2023-10-05","cited_by_count":25,"area":"agents"},{"id":"2311.00710","title":"Interactive AI Alignment: Specification, Process, and Evaluation Alignment","created":"2023-10-23","cited_by_count":22,"area":null},{"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":"1912.03553","title":"Learning Norms from Stories: A Prior for Value Aligned Agents","created":"2019-12-07","cited_by_count":19,"area":"alignment"},{"id":"2507.05619","title":"Detecting Proxy Gaming in RL and LLM Alignment via Evaluator Stress Tests","created":"2025-07-08","cited_by_count":19,"area":"alignment"},{"id":"2104.09469","title":"Training Value-Aligned Reinforcement Learning Agents Using a Normative Prior","created":"2021-04-19","cited_by_count":14,"area":null},{"id":"2405.10729","title":"Contestable AI needs Computational Argumentation","created":"2024-05-17","cited_by_count":13,"area":null},{"id":"2205.04525","title":"Towards a multi-stakeholder value-based assessment framework for algorithmic systems","created":"2022-05-09","cited_by_count":12,"area":null},{"id":"2501.11739","title":"Episodic memory in AI agents poses risks that should be studied and mitigated","created":"2025-01-20","cited_by_count":11,"area":null},{"id":"2305.19861","title":"Human Control: Definitions and Algorithms","created":"2023-05-31","cited_by_count":10,"area":null},{"id":"2407.06235","title":"Auditing of AI: Legal, Ethical and Technical Approaches","created":"2024-07-07","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":"2505.04950","title":"Epistemic Artificial Intelligence is Essential for Machine Learning Models to Truly 'Know When They Do Not Know'","created":"2025-05-08","cited_by_count":8,"area":null},{"id":"1911.04220","title":"Non-Cooperative Inverse Reinforcement Learning","created":"2019-11-03","cited_by_count":7,"area":"offlinerl"},{"id":"2109.11018","title":"Making Human-Like Trade-offs in Constrained Environments by Learning from Demonstrations","created":"2021-09-22","cited_by_count":7,"area":"offlinerl"},{"id":"2111.02907","title":"Model-Free Risk-Sensitive Reinforcement Learning","created":"2021-11-04","cited_by_count":7,"area":null},{"id":"2402.16751","title":"Value Preferences Estimation and Disambiguation in Hybrid Participatory Systems","created":"2024-02-26","cited_by_count":7,"area":null},{"id":"2405.11612","title":"Sociotechnical Implications of Generative Artificial Intelligence for Information Access","created":"2024-05-19","cited_by_count":6,"area":null},{"id":"2101.10865","title":"On managing vulnerabilities in AI/ML systems","created":"2021-01-22","cited_by_count":5,"area":null},{"id":"2105.06551","title":"Axes for Sociotechnical Inquiry in AI Research","created":"2021-04-26","cited_by_count":5,"area":null},{"id":"2201.07763","title":"When Is It Acceptable to Break the Rules? Knowledge Representation of Moral Judgement Based on Empirical Data","created":"2022-01-19","cited_by_count":5,"area":null},{"id":"2302.02788","title":"A Strong Baseline for Batch Imitation Learning","created":"2023-02-06","cited_by_count":5,"area":"offlinerl"},{"id":"2502.05934","title":"Intrinsic Barriers and Practical Pathways for Human-AI Alignment: An Agreement-Based Complexity Analysis","created":"2025-02-09","cited_by_count":5,"area":"alignment"},{"id":"2601.10520","title":"Breaking Up with Normatively Monolithic Agency with GRACE: A Reason-Based Neuro-Symbolic Architecture for Safe and Ethical AI Alignment","created":"2026-01-15","cited_by_count":5,"area":"lr"},{"id":"2103.03938","title":"Causal Analysis of Agent Behavior for AI Safety","created":"2021-03-05","cited_by_count":4,"area":null},{"id":"2508.00238","title":"Model Misalignment and Language Change: Traces of AI-Associated Language in Unscripted Spoken English","created":"2025-08-01","cited_by_count":4,"area":null},{"id":"2503.05724","title":"Addressing Moral Uncertainty using Large Language Models for Ethical Decision-Making","created":"2025-02-17","cited_by_count":3,"area":null},{"id":"2505.10670","title":"Interpretable Risk Mitigation in LLM Agent Systems","created":"2025-05-15","cited_by_count":3,"area":"agents"},{"id":"2103.05434","title":"When is it permissible for artificial intelligence to lie? A trust-based approach","created":"2021-03-09","cited_by_count":2,"area":null},{"id":"2202.10407","title":"Learning Behavioral Soft Constraints from Demonstrations","created":"2022-02-21","cited_by_count":2,"area":null},{"id":"2312.09402","title":"CERN for AI: A Theoretical Framework for Autonomous Simulation-Based Artificial Intelligence Testing and Alignment","created":"2023-12-14","cited_by_count":2,"area":null},{"id":"2505.13182","title":"Information Science Principles of Machine Learning: A Causal Chain Meta-Framework Based on Formalized Information Mapping","created":"2025-05-19","cited_by_count":2,"area":null},{"id":"2508.21443","title":"Beyond expected value: geometric mean optimization for long-term policy performance in reinforcement learning","created":"2025-08-29","cited_by_count":2,"area":"deeprl"},{"id":"2602.01474","title":"Legal Infrastructure for Transformative AI Governance","created":"2026-02-01","cited_by_count":2,"area":null},{"id":"2201.04632","title":"The Concept of Criticality in AI Safety","created":"2022-01-12","cited_by_count":1,"area":null},{"id":"2301.06421","title":"AI Alignment Dialogues: An Interactive Approach to AI Alignment in Support Agents","created":"2023-01-16","cited_by_count":1,"area":null},{"id":"2311.05754","title":"Deep Natural Language Feature Learning for Interpretable Prediction","created":"2023-11-09","cited_by_count":1,"area":null},{"id":"2408.08995","title":"On the Undecidability of Artificial Intelligence Alignment: Machines that Halt","created":"2024-08-16","cited_by_count":1,"area":"alignment"},{"id":"2411.04127","title":"Combining Theory of Mind and Kindness for Self-Supervised Human-AI Alignment","created":"2024-10-21","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":"2503.04569","title":"ValuePilot: A Two-Phase Framework for Value-Driven Decision-Making","created":"2025-03-06","cited_by_count":1,"area":null},{"id":"2504.15125","title":"Contemplative Artificial Intelligence","created":"2025-04-21","cited_by_count":1,"area":null},{"id":"2508.19317","title":"What Makes AI Applications Acceptable or Unacceptable? A Predictive Moral Framework","created":"2025-08-26","cited_by_count":1,"area":null},{"id":"2512.02966","title":"Lumos: Let there be Language Model System Certification","created":"2025-12-02","cited_by_count":1,"area":null},{"id":"2512.12921","title":"Cisco Integrated AI Security and Safety Framework Report","created":"2025-12-15","cited_by_count":1,"area":null},{"id":"1809.01036","title":"A Roadmap for Robust End-to-End Alignment","created":"2018-09-04","cited_by_count":0,"area":"alignment"},{"id":"2105.07405","title":"Robust optimal policies for team Markov games","created":"2021-05-16","cited_by_count":0,"area":null},{"id":"2111.00585","title":"JEDAI: A System for Skill-Aligned Explainable Robot Planning","created":"2021-10-31","cited_by_count":0,"area":null},{"id":"2208.09953","title":"Do-AIQ: A Design-of-Experiment Approach to Quality Evaluation of AI Mislabel Detection Algorithm","created":"2022-08-21","cited_by_count":0,"area":null},{"id":"2212.06048","title":"Machine Learning Approaches for Principle Prediction in Naturally Occurring Stories","created":"2022-11-19","cited_by_count":0,"area":null},{"id":"2305.07511","title":"eXplainable Artificial Intelligence on Medical Images: A Survey","created":"2023-05-12","cited_by_count":0,"area":null},{"id":"2306.13004","title":"Can Differentiable Decision Trees Enable Interpretable Reward Learning from Human Feedback?","created":"2023-06-22","cited_by_count":0,"area":"alignment"},{"id":"2309.12321","title":"A Case for AI Safety via Law","created":"2023-07-31","cited_by_count":0,"area":null},{"id":"2407.05341","title":"The Switch, the Ladder, and the Matrix: Models for Classifying AI Systems","created":"2024-07-07","cited_by_count":0,"area":null},{"id":"2501.09707","title":"The Goofus & Gallant Story Corpus for Practical Value Alignment","created":"2025-01-16","cited_by_count":0,"area":null},{"id":"2504.13979","title":"Framework, Standards, Applications and Best practices of Responsible AI : A Comprehensive Survey","created":"2025-04-18","cited_by_count":0,"area":null},{"id":"2509.13356","title":"CogniAlign: Survivability-Grounded Multi-Agent Moral Reasoning for Safe and Transparent AI","created":"2025-09-14","cited_by_count":0,"area":"agents"},{"id":"2512.08449","title":"From Accuracy to Impact: The Impact-Driven AI Framework (IDAIF) for Aligning Engineering Architecture with Theory of Change","created":"2025-12-09","cited_by_count":0,"area":null},{"id":"2512.13716","title":"ValuePilot: A Two-Phase Framework for Value-Driven Decision-Making","created":"2025-12-09","cited_by_count":0,"area":null},{"id":"2512.16873","title":"The Social Responsibility Stack: A Control-Theoretic Architecture for Governing Socio-Technical AI","created":"2025-12-18","cited_by_count":0,"area":null},{"id":"2604.20867","title":"Preserving Decision Sovereignty in Military AI: A Trade-Secret-Safe Architectural Framework for Model Replaceability, Human Authority, and State Control","created":"2026-03-26","cited_by_count":0,"area":null},{"id":"2604.22227","title":"A Co-Evolutionary Theory of Human-AI Coexistence: Mutualism, Governance, and Dynamics in Complex Societies","created":"2026-04-24","cited_by_count":0,"area":null},{"id":"2605.00440","title":"Role-Aware Artificial Intelligence Across Augmentation and Automation in Human-Machine Symbiosis","created":"2026-05-01","cited_by_count":0,"area":null},{"id":"2606.03165","title":"Fully Automated Identification of Lexical Alignment and Preference-Stage Shifts in Large Language Models","created":"2026-06-02","cited_by_count":0,"area":"alignment"},{"id":"2608.07642","title":"Contextual Value Alignment via Multilayer Combinatorial Fusion","created":"2026-08-07","cited_by_count":0,"area":"alignment"},{"id":"2609.13731","title":"Trustworthy Agentic AI: A Comprehensive Cybersecurity and Systems Survey on Threat Landscapes, Defense Architectures, and Open Challenges","created":"2026-09-12","cited_by_count":0,"area":"agents"}],"next_cursor":null}