{"total":34,"rows":[{"id":"2501.14249","title":"Humanity's Last Exam","created":"2025-01-24","cited_by_count":491,"area":null},{"id":"2304.03279","title":"Do the Rewards Justify the Means? Measuring Trade-Offs Between Rewards and Ethical Behavior in the MACHIAVELLI Benchmark","created":"2023-04-06","cited_by_count":182,"area":null},{"id":"2311.18232","title":"LMRL Gym: Benchmarks for Multi-Turn Reinforcement Learning with Language Models","created":"2023-11-30","cited_by_count":88,"area":null},{"id":"2206.05862","title":"X-Risk Analysis for AI Research","created":"2022-06-13","cited_by_count":60,"area":null},{"id":"2308.01404","title":"Hoodwinked: Deception and Cooperation in a Text-Based Game for Language Models","created":"2023-07-05","cited_by_count":47,"area":null},{"id":"2408.02373","title":"Operationalizing Contextual Integrity in Privacy-Conscious Assistants","created":"2024-08-05","cited_by_count":37,"area":null},{"id":"2209.08025","title":"Trustworthy Reinforcement Learning Against Intrinsic Vulnerabilities: Robustness, Safety, and Generalizability","created":"2022-09-16","cited_by_count":36,"area":null},{"id":"2205.01975","title":"Aligning to Social Norms and Values in Interactive Narratives","created":"2022-05-04","cited_by_count":32,"area":null},{"id":"2205.12630","title":"Multimodal Knowledge Alignment with Reinforcement Learning","created":"2022-05-25","cited_by_count":30,"area":null},{"id":"2305.11598","title":"Introspective Tips: Large Language Model for In-Context Decision Making","created":"2023-05-19","cited_by_count":28,"area":null},{"id":"2303.16200","title":"Natural Selection Favors AIs over Humans","created":"2023-03-28","cited_by_count":24,"area":null},{"id":"2310.15431","title":"What Makes it Ok to Set a Fire? Iterative Self-distillation of Contexts and Rationales for Disambiguating Defeasible Social and Moral Situations","created":"2023-10-24","cited_by_count":15,"area":null},{"id":"2310.13915","title":"Values, Ethics, Morals? On the Use of Moral Concepts in NLP Research","created":"2023-10-21","cited_by_count":14,"area":null},{"id":"2212.06295","title":"Despite \"super-human\" performance, current LLMs are unsuited for decisions about ethics and safety","created":"2022-12-13","cited_by_count":13,"area":null},{"id":"2411.05214","title":"STAND-Guard: A Small Task-Adaptive Content Moderation Model","created":"2024-11-07","cited_by_count":12,"area":null},{"id":"2507.23701","title":"TextQuests: How Good are LLMs at Text-Based Video Games?","created":"2025-07-31","cited_by_count":12,"area":null},{"id":"2506.13082","title":"Discerning What Matters: A Multi-Dimensional Assessment of Moral Competence in LLMs","created":"2025-06-16","cited_by_count":10,"area":null},{"id":"2210.10039","title":"How Would The Viewer Feel? Estimating Wellbeing From Video Scenarios","created":"2022-10-18","cited_by_count":9,"area":null},{"id":"2503.00940","title":"Can AI Model the Complexities of Human Moral Decision-Making? A Qualitative Study of Kidney Allocation Decisions","created":"2025-03-02","cited_by_count":9,"area":null},{"id":"2506.17434","title":"Resource Rational Contractualism Should Guide AI Alignment","created":"2025-06-20","cited_by_count":8,"area":null},{"id":"2312.14106","title":"Learning Human-like Representations to Enable Learning Human Values","created":"2023-12-21","cited_by_count":7,"area":null},{"id":"2510.00857","title":"ManagerBench: Evaluating the Safety-Pragmatism Trade-off in Autonomous LLMs","created":"2025-10-01","cited_by_count":6,"area":null},{"id":"2210.10684","title":"Language Models Understand Us, Poorly","created":"2022-10-19","cited_by_count":3,"area":null},{"id":"2509.23166","title":"Test-Time Policy Adaptation for Enhanced Multi-Turn Interactions with LLMs","created":"2025-09-27","cited_by_count":3,"area":null},{"id":"2112.01575","title":"Towards Interactive Reinforcement Learning with Intrinsic Feedback","created":"2021-12-02","cited_by_count":2,"area":null},{"id":"2304.07258","title":"Learn What Is Possible, Then Choose What Is Best: Disentangling One-To-Many Relations in Language Through Text-based Games","created":"2023-04-14","cited_by_count":2,"area":null},{"id":"2312.03726","title":"Interpretation modeling: Social grounding of sentences by reasoning over their implicit moral judgments","created":"2023-11-27","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":"2410.05496","title":"Intuitions of Compromise: Utilitarianism vs. Contractualism","created":"2024-10-07","cited_by_count":1,"area":null},{"id":"2504.06868","title":"Persona Dynamics: Unveiling the Impact of Personality Traits on Agents in Text-Based Games","created":"2025-04-09","cited_by_count":1,"area":null},{"id":"2307.10315","title":"Absolutist AI","created":"2023-07-19","cited_by_count":0,"area":null},{"id":"2407.07671","title":"Why should we ever automate moral decision making?","created":"2024-07-10","cited_by_count":0,"area":null},{"id":"2408.12250","title":"Can Artificial Intelligence Embody Moral Values?","created":"2024-08-22","cited_by_count":0,"area":null},{"id":"2603.08024","title":"ConflictBench: Evaluating Human-AI Conflict via Interactive and Visually Grounded Environments","created":"2026-03-09","cited_by_count":0,"area":null}],"next_cursor":null}