{"total":39,"rows":[{"id":"1706.03741","title":"Deep reinforcement learning from human preferences","created":"2017-06-12","cited_by_count":3912,"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":"1811.07871","title":"Scalable agent alignment via reward modeling: a research direction","created":"2018-11-19","cited_by_count":447,"area":"alignment"},{"id":"2209.13085","title":"Defining and Characterizing Reward Hacking","created":"2022-09-27","cited_by_count":203,"area":"alignment"},{"id":"2310.13595","title":"The History and Risks of Reinforcement Learning and Human Feedback","created":"2023-10-20","cited_by_count":42,"area":"alignment"},{"id":"2009.14715","title":"Learning Rewards from Linguistic Feedback","created":"2020-09-30","cited_by_count":41,"area":"alignment"},{"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":"2406.01309","title":"REvolve: Reward Evolution with Large Language Models using Human Feedback","created":"2024-06-03","cited_by_count":23,"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":"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":"2405.08154","title":"LLM Theory of Mind and Alignment: Opportunities and Risks","created":"2024-05-13","cited_by_count":18,"area":"alignment"},{"id":"2402.17747","title":"When Your AIs Deceive You: Challenges of Partial Observability in Reinforcement Learning from Human Feedback","created":"2024-02-27","cited_by_count":17,"area":"alignment"},{"id":"2101.07691","title":"Choice Set Misspecification in Reward Inference","created":"2021-01-19","cited_by_count":13,"area":"alignment"},{"id":"2412.16468","title":"The Road to Artificial SuperIntelligence: A Comprehensive Survey of Superalignment","created":"2024-12-21","cited_by_count":13,"area":"alignment"},{"id":"2412.08812","title":"Test-Time Alignment via Hypothesis Reweighting","created":"2024-12-11","cited_by_count":11,"area":"alignment"},{"id":"2401.08672","title":"Concept Alignment","created":"2024-01-09","cited_by_count":10,"area":"alignment"},{"id":"2504.07091","title":"AssistanceZero: Scalably Solving Assistance Games","created":"2025-04-09","cited_by_count":10,"area":"alignment"},{"id":"2402.17975","title":"Sample-Efficient Preference-based Reinforcement Learning with Dynamics Aware Rewards","created":"2024-02-28","cited_by_count":9,"area":"alignment"},{"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":"2211.06527","title":"Rewards Encoding Environment Dynamics Improves Preference-based Reinforcement Learning","created":"2022-11-12","cited_by_count":4,"area":"alignment"},{"id":"2510.04073","title":"Moral Anchor System: A Predictive Framework for AI Value Alignment and Drift Prevention","created":"2025-10-05","cited_by_count":3,"area":"alignment"},{"id":"2209.14010","title":"Argumentative Reward Learning: Reasoning About Human Preferences","created":"2022-09-28","cited_by_count":2,"area":"alignment"},{"id":"2410.14807","title":"Aligning AI Agents via Information-Directed Sampling","created":"2024-10-18","cited_by_count":2,"area":"alignment"},{"id":"2404.08791","title":"Expectation Alignment: Handling Reward Misspecification in the Presence of Expectation Mismatch","created":"2024-04-12","cited_by_count":1,"area":"alignment"},{"id":"2409.07335","title":"Explanation, Debate, Align: A Weak-to-Strong Framework for Language Model Generalization","created":"2024-09-11","cited_by_count":1,"area":"alignment"},{"id":"2503.07660","title":"Research Superalignment Should Advance Now with Alternating Competence and Conformity Optimization","created":"2025-03-08","cited_by_count":1,"area":"alignment"},{"id":"2508.15693","title":"NiceWebRL: a Python library for human subject experiments with reinforcement learning environments","created":"2025-08-21","cited_by_count":1,"area":"alignment"},{"id":"2512.03048","title":"The Specification Trap: Why Static Value Alignment Alone Is Insufficient for Robust Alignment","created":"2025-11-19","cited_by_count":1,"area":"alignment"},{"id":"2604.26360","title":"Uncertainty-Aware Reward Discounting for Mitigating Reward Hacking","created":"2026-04-29","cited_by_count":1,"area":"alignment"},{"id":"2607.00001","title":"Constructive Alignment: Governing Preference Dynamics in Human-AI Interaction","created":"2026-04-01","cited_by_count":1,"area":"alignment"},{"id":"2607.04590","title":"Attention Limited Reward Learning","created":"2026-07-06","cited_by_count":1,"area":"alignment"},{"id":"1809.01036","title":"A Roadmap for Robust End-to-End Alignment","created":"2018-09-04","cited_by_count":0,"area":"alignment"},{"id":"2505.15626","title":"Direct Preference Optimization for Adaptive Concept-based Explanations","created":"2025-05-21","cited_by_count":0,"area":"alignment"},{"id":"2508.06592","title":"Towards Integrated Alignment","created":"2025-08-08","cited_by_count":0,"area":"alignment"},{"id":"2509.12179","title":"Co-Alignment: Rethinking Alignment as Bidirectional Human-AI Cognitive Adaptation","created":"2025-09-15","cited_by_count":0,"area":"alignment"},{"id":"2608.10327","title":"Toward a Theory of Value in AI Alignment","created":"2026-08-10","cited_by_count":0,"area":"alignment"},{"id":"2609.05009","title":"Language models judge war differently when tested for alignment","created":"2026-09-04","cited_by_count":0,"area":"alignment"},{"id":"2609.23640","title":"Are Human-Aligned Models Models of Humans? A Turing-Test Gap in Preference Alignment","created":"2026-09-20","cited_by_count":0,"area":"alignment"}],"next_cursor":null}