{"total":74,"rows":[{"id":"2406.05946","title":"Safety Alignment Should Be Made More Than Just a Few Tokens Deep","created":"2024-06-10","cited_by_count":472,"area":"alignment"},{"id":"2312.14925","title":"A Survey of Reinforcement Learning from Human Feedback","created":"2023-12-22","cited_by_count":264,"area":"alignment"},{"id":"2406.15513","title":"PKU-SafeRLHF: Towards Multi-Level Safety Alignment for LLMs with Human Preference","created":"2024-06-20","cited_by_count":261,"area":"alignment"},{"id":"2402.02416","title":"Aligner: Efficient Alignment by Learning to Correct","created":"2024-02-04","cited_by_count":98,"area":"alignment"},{"id":"2402.02030","title":"Panacea: Pareto Alignment via Preference Adaptation for LLMs","created":"2024-02-03","cited_by_count":80,"area":"alignment"},{"id":"2402.16192","title":"Defending Large Language Models against Jailbreak Attacks via Semantic Smoothing","created":"2024-02-25","cited_by_count":74,"area":"alignment"},{"id":"2406.08469","title":"PAL: Pluralistic Alignment Framework for Learning from Heterogeneous Preferences","created":"2024-06-12","cited_by_count":54,"area":"alignment"},{"id":"2504.12328","title":"A Comprehensive Survey of Reward Models: Taxonomy, Applications, Challenges, and Future","created":"2025-04-12","cited_by_count":53,"area":"alignment"},{"id":"2410.04350","title":"TIS-DPO: Token-level Importance Sampling for Direct Preference Optimization With Estimated Weights","created":"2024-10-06","cited_by_count":42,"area":"alignment"},{"id":"2404.09824","title":"Impact of Preference Noise on the Alignment Performance of Generative Language Models","created":"2024-04-15","cited_by_count":41,"area":"alignment"},{"id":"2412.15838","title":"Align Anything: Training All-Modality Models to Follow Instructions with Language Feedback","created":"2024-12-20","cited_by_count":39,"area":"alignment"},{"id":"2505.20065","title":"SafeDPO: A Simple Approach to Direct Preference Optimization with Enhanced Safety","created":"2025-05-26","cited_by_count":37,"area":"alignment"},{"id":"2408.11779","title":"Personality Alignment of Large Language Models","created":"2024-08-21","cited_by_count":36,"area":"alignment"},{"id":"2503.11701","title":"A Survey of Direct Preference Optimization","created":"2025-03-12","cited_by_count":36,"area":"alignment"},{"id":"2409.00598","title":"Automatic Pseudo-Harmful Prompt Generation for Evaluating False Refusals in Large Language Models","created":"2024-09-01","cited_by_count":35,"area":"alignment"},{"id":"2404.11049","title":"Stepwise Alignment for Constrained Language Model Policy Optimization","created":"2024-04-17","cited_by_count":30,"area":"alignment"},{"id":"2408.04655","title":"Strong and weak alignment of large language models with human values","created":"2024-08-05","cited_by_count":27,"area":"alignment"},{"id":"2409.19605","title":"The Crucial Role of Samplers in Online Direct Preference Optimization","created":"2024-09-29","cited_by_count":27,"area":"alignment"},{"id":"2406.11191","title":"A Survey on Human Preference Learning for Large Language Models","created":"2024-06-17","cited_by_count":24,"area":"alignment"},{"id":"2406.11431","title":"Super(ficial)-alignment: Strong Models May Deceive Weak Models in Weak-to-Strong Generalization","created":"2024-06-17","cited_by_count":23,"area":"alignment"},{"id":"2506.01080","title":"The Coming Crisis of Multi-Agent Misalignment: AI Alignment Must Be a Dynamic and Social Process","created":"2025-06-01","cited_by_count":21,"area":"alignment"},{"id":"2403.18742","title":"Understanding the Learning Dynamics of Alignment with Human Feedback","created":"2024-03-27","cited_by_count":15,"area":"alignment"},{"id":"2503.18130","title":"Mitigating Reward Over-Optimization in RLHF via Behavior-Supported Regularization","created":"2025-03-23","cited_by_count":14,"area":"alignment"},{"id":"2411.12843","title":"Reward Modeling with Ordinal Feedback: Wisdom of the Crowd","created":"2024-11-19","cited_by_count":11,"area":"alignment"},{"id":"2412.15623","title":"JailPO: A Novel Black-box Jailbreak Framework via Preference Optimization against Aligned LLMs","created":"2024-12-20","cited_by_count":11,"area":"alignment"},{"id":"2405.11647","title":"Hummer: Towards Limited Competitive Preference Dataset","created":"2024-05-19","cited_by_count":10,"area":"alignment"},{"id":"2507.20333","title":"The Blessing and Curse of Dimensionality in Safety Alignment","created":"2025-07-27","cited_by_count":10,"area":"alignment"},{"id":"2404.18870","title":"More RLHF, More Trust? On The Impact of Preference Alignment On Trustworthiness","created":"2024-04-29","cited_by_count":9,"area":"alignment"},{"id":"2409.00162","title":"Sequence to Sequence Reward Modeling: Improving RLHF by Language Feedback","created":"2024-08-30","cited_by_count":9,"area":"alignment"},{"id":"2505.17072","title":"Safety Alignment Can Be Not Superficial With Explicit Safety Signals","created":"2025-05-19","cited_by_count":9,"area":"alignment"},{"id":"2405.18718","title":"Efficient Model-agnostic Alignment via Bayesian Persuasion","created":"2024-05-29","cited_by_count":8,"area":"alignment"},{"id":"2405.21040","title":"Direct Alignment of Language Models via Quality-Aware Self-Refinement","created":"2024-05-31","cited_by_count":7,"area":"alignment"},{"id":"2408.03459","title":"Can DPO Learn Diverse Human Values? A Theoretical Scaling Law","created":"2024-08-06","cited_by_count":7,"area":"alignment"},{"id":"2508.08509","title":"Steerable Pluralism: Pluralistic Alignment via Few-Shot Comparative Regression","created":"2025-08-11","cited_by_count":7,"area":"alignment"},{"id":"2511.02109","title":"Deep Value Benchmark: Measuring Whether Models Generalize Deep Values or Shallow Preferences","created":"2025-11-03","cited_by_count":6,"area":"alignment"},{"id":"2511.10032","title":"Moral Change or Noise? On Problems of Aligning AI With Temporally Unstable Human Feedback","created":"2025-11-13","cited_by_count":6,"area":"alignment"},{"id":"2602.14777","title":"Emergently Misaligned Language Models Show Behavioral Self-Awareness That Shifts With Subsequent Realignment","created":"2026-02-16","cited_by_count":6,"area":"alignment"},{"id":"2602.22554","title":"Multilingual Safety Alignment Via Sparse Weight Editing","created":"2026-02-26","cited_by_count":6,"area":"alignment"},{"id":"2410.01957","title":"Challenges and Future Directions of Data-Centric AI Alignment","created":"2024-10-02","cited_by_count":5,"area":"alignment"},{"id":"2410.19933","title":"Enhancing Safety in Reinforcement Learning with Human Feedback via Rectified Policy Optimization","created":"2024-10-25","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":"2603.12595","title":"Swap-guided Preference Learning for Personalized Reinforcement Learning from Human Feedback","created":"2026-03-13","cited_by_count":5,"area":"alignment"},{"id":"2410.02451","title":"Strong Preferences Affect the Robustness of Preference Models and Value Alignment","created":"2024-10-03","cited_by_count":4,"area":"alignment"},{"id":"2502.19255","title":"Can RLHF be More Efficient with Imperfect Reward Models? A Policy Coverage Perspective","created":"2025-02-26","cited_by_count":4,"area":"alignment"},{"id":"2505.23950","title":"InterMT: Multi-Turn Interleaved Preference Alignment with Human Feedback","created":"2025-05-29","cited_by_count":4,"area":"alignment"},{"id":"2602.07340","title":"Revisiting Robustness for LLM Safety Alignment via Selective Geometry Control","created":"2026-02-07","cited_by_count":4,"area":"alignment"},{"id":"2406.01931","title":"Dishonesty in Helpful and Harmless Alignment","created":"2024-06-04","cited_by_count":3,"area":"alignment"},{"id":"2406.11039","title":"Dynamic Normativity: Necessary and Sufficient Conditions for Value Alignment","created":"2024-06-16","cited_by_count":3,"area":"alignment"},{"id":"2502.02153","title":"Vulnerability Mitigation for Safety-Aligned Language Models via Debiasing","created":"2025-02-04","cited_by_count":3,"area":"alignment"},{"id":"2503.10927","title":"OASST-ETC Dataset: Alignment Signals from Eye-tracking Analysis of LLM Responses","created":"2025-03-13","cited_by_count":3,"area":"alignment"},{"id":"2510.01458","title":"How Well Can Preference Optimization Generalize Under Noisy Feedback?","created":"2025-10-01","cited_by_count":3,"area":"alignment"},{"id":"2511.06222","title":"SPA: Achieving Consensus in LLM Alignment via Self-Priority Optimization","created":"2025-11-09","cited_by_count":3,"area":"alignment"},{"id":"2409.18417","title":"VickreyFeedback: Cost-efficient Data Construction for Reinforcement Learning from Human Feedback","created":"2024-09-27","cited_by_count":2,"area":"alignment"},{"id":"2501.05336","title":"Stream Aligner: Efficient Sentence-Level Alignment via Distribution Induction","created":"2025-01-09","cited_by_count":2,"area":"alignment"},{"id":"2509.11311","title":"Prompts to Proxies: Emulating Human Preferences via a Compact LLM Ensemble","created":"2025-09-14","cited_by_count":2,"area":"alignment"},{"id":"2510.07884","title":"Contrastive Weak-to-strong Generalization","created":"2025-10-09","cited_by_count":2,"area":"alignment"},{"id":"2511.11551","title":"Aligning Machiavellian Agents: Behavior Steering via Test-Time Policy Shaping","created":"2025-11-14","cited_by_count":2,"area":"alignment"},{"id":"2402.03282","title":"A Theoretical Framework for Partially Observed Reward-States in RLHF","created":"2024-02-05","cited_by_count":1,"area":"alignment"},{"id":"2406.16258","title":"MEReQ: Max-Ent Residual-Q Inverse RL for Sample-Efficient Alignment from Intervention","created":"2024-06-24","cited_by_count":1,"area":"alignment"},{"id":"2412.16475","title":"When Can Proxies Improve the Sample Complexity of Preference Learning?","created":"2024-12-21","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":"2510.23334","title":"Adaptive Blockwise Search: Inference-Time Alignment for Large Language Models","created":"2025-10-27","cited_by_count":1,"area":"alignment"},{"id":"2604.26511","title":"Tatemae: Detecting Alignment Faking via Tool Selection in LLMs","created":"2026-04-29","cited_by_count":1,"area":"alignment"},{"id":"2607.07023","title":"Online Data Selection Is Implicit Alignment","created":"2026-07-08","cited_by_count":1,"area":"alignment"},{"id":"2405.14103","title":"Online Self-Preferring Language Models","created":"2024-05-23","cited_by_count":0,"area":"alignment"},{"id":"2506.01692","title":"A Descriptive and Normative Theory of Human Beliefs in RLHF","created":"2025-06-02","cited_by_count":0,"area":"alignment"},{"id":"2508.06592","title":"Towards Integrated Alignment","created":"2025-08-08","cited_by_count":0,"area":"alignment"},{"id":"2509.07642","title":"Getting In Contract with Large Language Models -- An Agency Theory Perspective On Large Language Model Alignment","created":"2025-09-09","cited_by_count":0,"area":"alignment"},{"id":"2512.24263","title":"Constrained Language Model Policy Optimization via Risk-aware Stepwise Alignment","created":"2025-12-30","cited_by_count":0,"area":"alignment"},{"id":"2605.07105","title":"Theoretical Limits of Language Model Alignment","created":"2026-05-08","cited_by_count":0,"area":"alignment"},{"id":"2605.17342","title":"Transitivity Meets Cyclicity: Explicit Preference Decomposition for Dynamic Large Language Model Alignment","created":"2026-05-17","cited_by_count":0,"area":"alignment"},{"id":"2605.19966","title":"Detecting Fluent Optimization-Based Adversarial Prompts via Sequential Entropy Changes","created":"2026-05-19","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":"2610.05461","title":"AI Safety via Debate is Compromised by Cognitive Biases","created":"2026-10-04","cited_by_count":0,"area":"alignment"}],"next_cursor":null}