{"total":25,"rows":[{"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":"2412.15280","title":"Context-DPO: Aligning Language Models for Context-Faithfulness","created":"2024-12-18","cited_by_count":50,"area":"alignment"},{"id":"2406.11801","title":"Safety Arithmetic: A Framework for Test-time Safety Alignment of Language Models by Steering Parameters and Activations","created":"2024-06-17","cited_by_count":32,"area":"alignment"},{"id":"2405.20653","title":"Mind the Inconspicuous: Revealing the Hidden Weakness in Aligned LLMs' Refusal Boundaries","created":"2024-05-31","cited_by_count":28,"area":"alignment"},{"id":"2407.08770","title":"Model Surgery: Modulating LLM's Behavior Via Simple Parameter Editing","created":"2024-07-11","cited_by_count":23,"area":"alignment"},{"id":"2406.09920","title":"Knowledge Editing in Language Models via Adapted Direct Preference Optimization","created":"2024-06-14","cited_by_count":17,"area":"alignment"},{"id":"2402.07896","title":"Suppressing Pink Elephants with Direct Principle Feedback","created":"2024-02-12","cited_by_count":15,"area":"alignment"},{"id":"2406.01514","title":"Decoupled Alignment for Robust Plug-and-Play Adaptation","created":"2024-06-03","cited_by_count":9,"area":"alignment"},{"id":"2502.16645","title":"CODESYNC: Synchronizing Large Language Models with Dynamic Code Evolution at Scale","created":"2025-02-23","cited_by_count":8,"area":"alignment"},{"id":"2503.02989","title":"Effectively Steer LLM To Follow Preference via Building Confident Directions","created":"2025-03-04","cited_by_count":7,"area":"alignment"},{"id":"2602.15823","title":"CrispEdit: Low-Curvature Projections for Scalable Non-Destructive LLM Editing","created":"2026-02-17","cited_by_count":5,"area":"alignment"},{"id":"2604.12359","title":"Compiling Activation Steering into Weights via Null-Space Constraints for Stealthy Backdoors","created":"2026-04-14","cited_by_count":4,"area":"alignment"},{"id":"2404.10306","title":"Balancing Speciality and Versatility: A Coarse to Fine Framework for Mitigating Catastrophic Forgetting in Large Language Models","created":"2024-04-16","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":"2602.13867","title":"Bridging the Multilingual Safety Divide: Efficient, Culturally-Aware Alignment for Global South Languages","created":"2026-02-14","cited_by_count":2,"area":"alignment"},{"id":"2506.13285","title":"DualEdit: Mitigating Safety Fallback in LLM Backdoor Editing via Affirmation-Refusal Regulation","created":"2025-06-16","cited_by_count":1,"area":"alignment"},{"id":"2604.27401","title":"Perturbation Probing: A Two-Pass-per-Prompt Diagnostic for FFN Behavioral Circuits in Aligned LLMs","created":"2026-04-30","cited_by_count":1,"area":"alignment"},{"id":"2605.16600","title":"Where Pretraining writes and Alignment reads: the asymmetry of Transformer weight space","created":"2026-05-15","cited_by_count":1,"area":"alignment"},{"id":"2508.01302","title":"Aligning Language Models with Real-time Knowledge Editing","created":"2025-08-02","cited_by_count":0,"area":"alignment"},{"id":"2508.02063","title":"TRACEALIGN -- Tracing the Drift: Attributing Alignment Failures to Training-Time Belief Sources in LLMs","created":"2025-08-04","cited_by_count":0,"area":"alignment"},{"id":"2605.04972","title":"Why Expert Alignment Is Hard: Evidence from Subjective Evaluation","created":"2026-05-06","cited_by_count":0,"area":"alignment"},{"id":"2608.17202","title":"Fool's Gold: Defensive Deception Against Safety-Removal Attacks on Open-Weight Models","created":"2026-08-17","cited_by_count":0,"area":"alignment"},{"id":"2609.16532","title":"Style-Debiased DPO: Updating LLM Knowledge with Factuality-Aware Synthetic Preference Data","created":"2026-09-15","cited_by_count":0,"area":"alignment"},{"id":"2609.36748","title":"Generalizable Lifelong Model Editing via Preference Optimization","created":"2026-09-29","cited_by_count":0,"area":"alignment"},{"id":"2610.02844","title":"DNAlign: Dynamic Null-Space Safe Alignment for LLMs","created":"2026-10-02","cited_by_count":0,"area":"alignment"}],"next_cursor":null}