{"total":21,"rows":[{"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":"2312.07000","title":"Alignment for Honesty","created":"2023-12-12","cited_by_count":74,"area":"alignment"},{"id":"2411.02306","title":"On Targeted Manipulation and Deception when Optimizing LLMs for User Feedback","created":"2024-11-04","cited_by_count":47,"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":"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":"2403.18742","title":"Understanding the Learning Dynamics of Alignment with Human Feedback","created":"2024-03-27","cited_by_count":15,"area":"alignment"},{"id":"2406.18346","title":"AI Alignment through Reinforcement Learning from Human Feedback? Contradictions and Limitations","created":"2024-06-26","cited_by_count":11,"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":"2410.01957","title":"Challenges and Future Directions of Data-Centric AI Alignment","created":"2024-10-02","cited_by_count":5,"area":"alignment"},{"id":"2406.06874","title":"Learning Reward and Policy Jointly from Demonstration and Preference Improves Alignment","created":"2024-06-11","cited_by_count":4,"area":"alignment"},{"id":"2604.13386","title":"Linear Probe Accuracy Scales with Model Size and Benefits from Multi-Layer Ensembling","created":"2026-04-15","cited_by_count":4,"area":"alignment"},{"id":"2311.08487","title":"Alignment is not sufficient to prevent large language models from generating harmful information: A psychoanalytic perspective","created":"2023-11-14","cited_by_count":3,"area":"alignment"},{"id":"2406.01931","title":"Dishonesty in Helpful and Harmless Alignment","created":"2024-06-04","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":"2507.09406","title":"Adversarial Activation Patching: A Framework for Detecting and Mitigating Emergent Deception in Safety-Aligned Transformers","created":"2025-07-12","cited_by_count":2,"area":"alignment"},{"id":"2509.23564","title":"Clean First, Align Later: Benchmarking Preference Data Cleaning for Reliable LLM Alignment","created":"2025-09-28","cited_by_count":2,"area":"alignment"},{"id":"2602.16987","title":"A testable framework for AI alignment: Simulation Theology as an engineered worldview for silicon-based agents","created":"2026-02-19","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":"2606.13755","title":"Position: Align AI to Our Aspirations, Not Our Flaws","created":"2026-06-11","cited_by_count":1,"area":"alignment"},{"id":"2508.06592","title":"Towards Integrated Alignment","created":"2025-08-08","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"}],"next_cursor":null}