{"total":59,"rows":[{"id":"1909.08593","title":"Fine-Tuning Language Models from Human Preferences","created":"2019-09-18","cited_by_count":2150,"area":"alignment"},{"id":"2112.09332","title":"WebGPT: Browser-assisted question-answering with human feedback","created":"2021-12-17","cited_by_count":1745,"area":"alignment"},{"id":"2112.00861","title":"A General Language Assistant as a Laboratory for Alignment","created":"2021-12-01","cited_by_count":1055,"area":"alignment"},{"id":"2212.09251","title":"Discovering Language Model Behaviors with Model-Written Evaluations","created":"2022-12-19","cited_by_count":836,"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":"2310.12773","title":"Safe RLHF: Safe Reinforcement Learning from Human Feedback","created":"2023-10-19","cited_by_count":656,"area":"alignment"},{"id":"2312.09390","title":"Weak-to-Strong Generalization: Eliciting Strong Capabilities With Weak Supervision","created":"2023-12-14","cited_by_count":467,"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":"2308.06463","title":"GPT-4 Is Too Smart To Be Safe: Stealthy Chat with LLMs via Cipher","created":"2023-08-12","cited_by_count":423,"area":"alignment"},{"id":"2310.01377","title":"UltraFeedback: Boosting Language Models with Scaled AI Feedback","created":"2023-10-02","cited_by_count":406,"area":"alignment"},{"id":"2402.06782","title":"Debating with More Persuasive LLMs Leads to More Truthful Answers","created":"2024-02-09","cited_by_count":266,"area":"alignment"},{"id":"2309.15025","title":"Large Language Model Alignment: A Survey","created":"2023-09-26","cited_by_count":243,"area":"alignment"},{"id":"2309.16240","title":"Beyond Reverse KL: Generalizing Direct Preference Optimization with Diverse Divergence Constraints","created":"2023-09-28","cited_by_count":174,"area":"alignment"},{"id":"2303.05453","title":"Personalisation within bounds: A risk taxonomy and policy framework for the alignment of large language models with personalised feedback","created":"2023-03-09","cited_by_count":87,"area":"alignment"},{"id":"2305.16960","title":"Training Socially Aligned Language Models on Simulated Social Interactions","created":"2023-05-26","cited_by_count":78,"area":"alignment"},{"id":"2408.16984","title":"Beyond Preferences in AI Alignment","created":"2024-08-30","cited_by_count":49,"area":"alignment"},{"id":"2406.16768","title":"WARP: On the Benefits of Weight Averaged Rewarded Policies","created":"2024-06-24","cited_by_count":45,"area":"alignment"},{"id":"2604.13602","title":"Reward Hacking in the Era of Large Models: Mechanisms, Emergent Misalignment, Challenges","created":"2026-04-15","cited_by_count":33,"area":"alignment"},{"id":"2310.13011","title":"Compositional preference models for aligning LMs","created":"2023-10-17","cited_by_count":26,"area":"alignment"},{"id":"2602.01002","title":"How RLHF Amplifies Sycophancy","created":"2026-02-01","cited_by_count":23,"area":"alignment"},{"id":"2407.14916","title":"Improving Context-Aware Preference Modeling for Language Models","created":"2024-07-20","cited_by_count":22,"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":"2403.06754","title":"ALaRM: Align Language Models via Hierarchical Rewards Modeling","created":"2024-03-11","cited_by_count":11,"area":"alignment"},{"id":"2503.00069","title":"Societal Alignment Frameworks Can Improve LLM Alignment","created":"2025-02-27","cited_by_count":8,"area":"alignment"},{"id":"2602.11180","title":"Mechanistic Interpretability for Large Language Model Alignment: Progress, Challenges, and Future Directions","created":"2026-01-21","cited_by_count":8,"area":"alignment"},{"id":"2406.18777","title":"Aligning Model Properties via Conformal Risk Control","created":"2024-06-26","cited_by_count":7,"area":"alignment"},{"id":"2201.08102","title":"Safe Deep RL in 3D Environments using Human Feedback","created":"2022-01-20","cited_by_count":5,"area":"alignment"},{"id":"2401.07181","title":"Reinforcement Learning from LLM Feedback to Counteract Goal Misgeneralization","created":"2024-01-14","cited_by_count":5,"area":"alignment"},{"id":"2501.07886","title":"Iterative Label Refinement Matters More than Preference Optimization under Weak Supervision","created":"2025-01-14","cited_by_count":5,"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":"2507.20964","title":"Core Safety Values for Provably Corrigible Agents","created":"2025-07-28","cited_by_count":5,"area":"alignment"},{"id":"2509.15090","title":"Emergent Alignment via Competition","created":"2025-09-18","cited_by_count":5,"area":"alignment"},{"id":"2502.04675","title":"Scalable Oversight for Superhuman AI via Recursive Self-Critiquing","created":"2025-02-07","cited_by_count":4,"area":"alignment"},{"id":"2606.24014","title":"Reinforcement Learning Towards Broadly and Persistently Beneficial Models","created":"2026-06-22","cited_by_count":4,"area":"alignment"},{"id":"2608.17776","title":"Debate Training Reduces Reward Hacking in RLAIF","created":"2026-08-18","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":"2603.05293","title":"Knowledge Divergence and the Value of Debate for Scalable Oversight","created":"2026-03-05","cited_by_count":2,"area":"alignment"},{"id":"2606.16276","title":"SpecAlign: Efficient Specification-Grounded Alignment of Large Language Models via Synthetic Data","created":"2026-06-15","cited_by_count":2,"area":"alignment"},{"id":"2403.02514","title":"The Autonomy-Alignment Problem in Open-Ended Learning Robots: Formalising the Purpose Framework","created":"2024-03-04","cited_by_count":1,"area":"alignment"},{"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":"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":"2503.13621","title":"Superalignment with Dynamic Human Values","created":"2025-03-17","cited_by_count":1,"area":"alignment"},{"id":"2507.14202","title":"PRM-Free Security Alignment of Large Models via Red Teaming and Adversarial Training","created":"2025-07-14","cited_by_count":1,"area":"alignment"},{"id":"2511.16202","title":"Multi-Agent Collaborative Reward Design for Enhancing Reasoning in Reinforcement Learning","created":"2025-11-20","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":"2606.28294","title":"Democratic ICAI: Debating Our Way to Steering Principles from Preferences","created":"2026-06-26","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":"2608.12645","title":"Jagged Judges: Epistemic Stability Under Perturbation, Pressure, and Persistence","created":"2026-08-12","cited_by_count":1,"area":"alignment"},{"id":"2402.15826","title":"Reward Design for Justifiable Sequential Decision-Making","created":"2024-02-24","cited_by_count":0,"area":"alignment"},{"id":"2508.06592","title":"Towards Integrated Alignment","created":"2025-08-08","cited_by_count":0,"area":"alignment"},{"id":"2509.00091","title":"Ensemble Debates with Local Large Language Models for AI Alignment","created":"2025-08-27","cited_by_count":0,"area":"alignment"},{"id":"2510.09330","title":"Safety Game: Inference-Time Alignment of Black-Box LLMs via Constrained Optimization","created":"2025-10-10","cited_by_count":0,"area":"alignment"},{"id":"2603.17378","title":"Efficient Exploration at Scale","created":"2026-03-18","cited_by_count":0,"area":"alignment"},{"id":"2605.04029","title":"Stayin' Aligned Over Time: Towards Longitudinal Human-LLM Alignment via Contextual Reflection and Privacy-Preserving Behavioral Data","created":"2026-05-05","cited_by_count":0,"area":"alignment"},{"id":"2606.07532","title":"Durable Evaluation Framework: Adversarial Arbitration for Sycophancy Reduction in Large Language Models","created":"2026-04-21","cited_by_count":0,"area":"alignment"},{"id":"2610.05461","title":"AI Safety via Debate is Compromised by Cognitive Biases","created":"2026-10-04","cited_by_count":0,"area":"alignment"},{"id":"2610.07935","title":"SIGMA: Self-Improving Alignment Generalization from a Model Spec","created":"2026-10-06","cited_by_count":0,"area":"alignment"}],"next_cursor":null}