{"total":36,"rows":[{"id":"2402.01694","title":"ARGS: Alignment as Reward-Guided Search","created":"2024-01-23","cited_by_count":103,"area":"alignment"},{"id":"2402.09267","title":"Self-Alignment for Factuality: Mitigating Hallucinations in LLMs via Self-Evaluation","created":"2024-02-14","cited_by_count":80,"area":"alignment"},{"id":"2402.02992","title":"Decoding-time Realignment of Language Models","created":"2024-02-05","cited_by_count":67,"area":"alignment"},{"id":"2405.09719","title":"Spectral Editing of Activations for Large Language Model Alignment","created":"2024-05-15","cited_by_count":56,"area":"alignment"},{"id":"2404.05875","title":"CodecLM: Aligning Language Models with Tailored Synthetic Data","created":"2024-04-08","cited_by_count":39,"area":"alignment"},{"id":"2402.12343","title":"Emulated Disalignment: Safety Alignment for Large Language Models May Backfire!","created":"2024-02-19","cited_by_count":37,"area":"alignment"},{"id":"2401.11458","title":"Linear Alignment: A Closed-form Solution for Aligning Human Preferences without Tuning and Feedback","created":"2024-01-21","cited_by_count":25,"area":"alignment"},{"id":"2409.18786","title":"A Survey on the Honesty of Large Language Models","created":"2024-09-27","cited_by_count":23,"area":"alignment"},{"id":"2412.02685","title":"T-REG: Preference Optimization with Token-Level Reward Regularization","created":"2024-12-03","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":"2506.12109","title":"Personalized LLM Decoding via Contrasting Personal Preference","created":"2025-06-13","cited_by_count":12,"area":"alignment"},{"id":"2305.17760","title":"Language Models are Bounded Pragmatic Speakers: Understanding RLHF from a Bayesian Cognitive Modeling Perspective","created":"2023-05-28","cited_by_count":10,"area":"alignment"},{"id":"2408.05094","title":"Unlocking Decoding-time Controllability: Gradient-Free Multi-Objective Alignment with Contrastive Prompts","created":"2024-08-09","cited_by_count":9,"area":"alignment"},{"id":"2406.16743","title":"Safety Alignment of Large Language Models via Contrasting Safe and Harmful Distributions","created":"2024-06-24","cited_by_count":8,"area":"alignment"},{"id":"2402.09320","title":"ICDPO: Effectively Borrowing Alignment Capability of Others via In-context Direct Preference Optimization","created":"2024-02-14","cited_by_count":6,"area":"alignment"},{"id":"2501.17295","title":"Mitigating Hallucinated Translations in Large Language Models with Hallucination-focused Preference Optimization","created":"2025-01-28","cited_by_count":6,"area":"alignment"},{"id":"2509.06982","title":"CARE: Decoding Time Safety Alignment via Rollback and Introspection Intervention","created":"2025-09-01","cited_by_count":6,"area":"alignment"},{"id":"2502.13177","title":"KL Penalty Control via Perturbation for Direct Preference Optimization","created":"2025-02-18","cited_by_count":5,"area":"alignment"},{"id":"2407.04181","title":"Orchestrating LLMs with Different Personalizations","created":"2024-07-04","cited_by_count":4,"area":"alignment"},{"id":"2510.04773","title":"Distribution Preference Optimization: A Fine-grained Perspective for LLM Unlearning","created":"2025-10-06","cited_by_count":3,"area":"alignment"},{"id":"2510.07884","title":"Contrastive Weak-to-strong Generalization","created":"2025-10-09","cited_by_count":2,"area":"alignment"},{"id":"2510.21883","title":"Language Ranker: A Lightweight Ranking framework for LLM Decoding","created":"2025-10-23","cited_by_count":2,"area":"alignment"},{"id":"2604.17132","title":"Please refuse to answer me! Mitigating Over-Refusal in Large Language Models via Adaptive Contrastive Decoding","created":"2026-04-18","cited_by_count":2,"area":"alignment"},{"id":"2606.21906","title":"Deeper is Not Always Better: Mitigating the Alignment Tax via Confident Layer Decoding","created":"2026-06-20","cited_by_count":2,"area":"alignment"},{"id":"2406.16377","title":"On the Transformations across Reward Model, Parameter Update, and In-Context Prompt","created":"2024-06-24","cited_by_count":1,"area":"alignment"},{"id":"2411.02481","title":"Dr. SoW: Density Ratio of Strong-over-weak LLMs for Reducing the Cost of Human Annotation in Preference Tuning","created":"2024-11-04","cited_by_count":1,"area":"alignment"},{"id":"2509.26169","title":"Alignment-Aware Decoding","created":"2025-09-30","cited_by_count":1,"area":"alignment"},{"id":"2510.16257","title":"Towards Low-Resource Alignment to Diverse Perspectives with Sparse Feedback","created":"2025-10-17","cited_by_count":1,"area":"alignment"},{"id":"2603.04355","title":"Efficient Refusal Ablation in LLM through Optimal Transport","created":"2026-03-04","cited_by_count":1,"area":"alignment"},{"id":"2609.05800","title":"Spillover-Aware Multi-Value Steering for Pluralistic LLM Alignment","created":"2026-09-05","cited_by_count":1,"area":"alignment"},{"id":"2609.05968","title":"Test-Time Weak-to-Strong Alignment: Transferring Implicit Rewards from Weak to Strong Flow Models","created":"2026-09-05","cited_by_count":1,"area":"alignment"},{"id":"2604.15577","title":"Reward Weighted Classifier-Free Guidance as Policy Improvement in Autoregressive Models","created":"2026-04-16","cited_by_count":0,"area":"alignment"},{"id":"2606.30339","title":"REAR: Test-time Preference Realignment through Reward Decomposition","created":"2026-06-29","cited_by_count":0,"area":"alignment"},{"id":"2609.00624","title":"Trust Your Guide Only When Certain: Uncertainty-Aware Sparse Alignment at Inference Time","created":"2026-09-01","cited_by_count":0,"area":"alignment"},{"id":"2609.01161","title":"CopyShield: A Cross-Level Benchmark of Copyright Defenses in LLMs","created":"2026-09-01","cited_by_count":0,"area":"alignment"},{"id":"2609.30226","title":"PoEM: Predicting RL Outcomes from Existing Policies","created":"2026-09-24","cited_by_count":0,"area":"alignment"}],"next_cursor":null}