{"total":34,"rows":[{"id":"2510.07743","title":"OpenRubrics: Towards Scalable Synthetic Rubric Generation for Reward Modeling and LLM Alignment","created":"2025-10-09","cited_by_count":132,"area":"alignment"},{"id":"2507.08794","title":"One Token to Fool LLM-as-a-Judge","created":"2025-07-11","cited_by_count":60,"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":"2510.17314","title":"Auto-Rubric: Learning From Implicit Weights to Explicit Rubrics for Reward Modeling","created":"2025-10-20","cited_by_count":30,"area":"alignment"},{"id":"2506.08123","title":"QA-LIGN: Aligning LLMs through Constitutionally Decomposed QA","created":"2025-06-09","cited_by_count":28,"area":"alignment"},{"id":"2502.11555","title":"Equilibrate RLHF: Towards Balancing Helpfulness-Safety Trade-off in Large Language Models","created":"2025-02-17","cited_by_count":22,"area":"alignment"},{"id":"2505.02666","title":"A Survey on Progress in LLM Alignment from the Perspective of Reward Design","created":"2025-05-05","cited_by_count":15,"area":"alignment"},{"id":"2507.14987","title":"AlphaAlign: Incentivizing Safety Alignment with Extremely Simplified Reinforcement Learning","created":"2025-07-20","cited_by_count":15,"area":"alignment"},{"id":"2412.16974","title":"Cannot or Should Not? Automatic Analysis of Refusal Composition in IFT/RLHF Datasets and Refusal Behavior of Black-Box LLMs","created":"2024-12-22","cited_by_count":11,"area":"alignment"},{"id":"2509.21319","title":"RLBFF: Binary Flexible Feedback to bridge between Human Feedback & Verifiable Rewards","created":"2025-09-25","cited_by_count":8,"area":"alignment"},{"id":"2603.11388","title":"Deactivating Refusal Triggers: Understanding and Mitigating Overrefusal in Safety Alignment","created":"2026-03-12","cited_by_count":7,"area":"alignment"},{"id":"2501.15453","title":"Data-adaptive Safety Rules for Training Reward Models","created":"2025-01-26","cited_by_count":6,"area":"alignment"},{"id":"2603.15646","title":"Alternating Reinforcement Learning with Contextual Rubric Rewards: Beyond the Scalarization Strategy","created":"2026-03-04","cited_by_count":6,"area":"alignment"},{"id":"2504.02193","title":"More is Less: The Pitfalls of Multi-Model Synthetic Preference Data in DPO Safety Alignment","created":"2025-04-03","cited_by_count":5,"area":"alignment"},{"id":"2503.20995","title":"ENCORE: Entropy-guided Reward Composition for Multi-head Safety Reward Models","created":"2025-03-26","cited_by_count":4,"area":"alignment"},{"id":"2506.08266","title":"Reinforcement Learning from Human Feedback with High-Confidence Safety Constraints","created":"2025-06-09","cited_by_count":4,"area":"alignment"},{"id":"2506.02460","title":"MidPO: Dual Preference Optimization for Safety and Helpfulness in Large Language Models via a Mixture of Experts Framework","created":"2025-06-03","cited_by_count":3,"area":"alignment"},{"id":"2604.13618","title":"C2: Scalable Rubric-Augmented Reward Modeling from Binary Preferences","created":"2026-04-15","cited_by_count":3,"area":"alignment"},{"id":"2605.05750","title":"RVPO: Risk-Sensitive Alignment via Variance Regularization","created":"2026-05-07","cited_by_count":3,"area":"alignment"},{"id":"2605.31328","title":"Reinforcement Learning Can Amplify Emergent Misalignment from Harmless Rewards","created":"2026-05-29","cited_by_count":3,"area":"alignment"},{"id":"2606.07705","title":"SAW: Stage-Aware Dynamic Weighting for Multi-Objective Reinforcement Learning in Large Language Models","created":"2026-06-05","cited_by_count":3,"area":"alignment"},{"id":"2608.27505","title":"A Survey on Rubric-Guided Reinforcement Learning for Language Models","created":"2026-08-27","cited_by_count":3,"area":"alignment"},{"id":"2507.17107","title":"Reinforcement Learning Fine-Tunes a Sparse Subnetwork in Large Language Models","created":"2025-07-23","cited_by_count":2,"area":"alignment"},{"id":"2511.09864","title":"Uncertainty-Guided Checkpoint Selection for Reinforcement Finetuning of Large Language Models","created":"2025-11-13","cited_by_count":2,"area":"alignment"},{"id":"2603.10938","title":"Safe RLHF Beyond Expectation: Stochastic Dominance for Universal Spectral Risk Control","created":"2026-03-11","cited_by_count":2,"area":"alignment"},{"id":"2411.10534","title":"Chain of Alignment: Integrating Public Will with Expert Intelligence for Language Model Alignment","created":"2024-11-15","cited_by_count":1,"area":"alignment"},{"id":"2506.06444","title":"Saffron-1: Safety Inference Scaling","created":"2025-06-06","cited_by_count":1,"area":"alignment"},{"id":"2606.19168","title":"Beyond Safe Data: Pretraining-Stage Alignment with Regular Safety Reflection","created":"2026-06-17","cited_by_count":1,"area":"alignment"},{"id":"2506.10020","title":"From Threat to Tool: Leveraging Refusal-Aware Injection Attacks for Safety Alignment","created":"2025-06-07","cited_by_count":0,"area":"alignment"},{"id":"2604.04144","title":"Many Preferences, Few Policies: Towards Scalable Language Model Personalization","created":"2026-04-05","cited_by_count":0,"area":"alignment"},{"id":"2605.20994","title":"Towards Context-Invariant Safety Alignment for Large Language Models","created":"2026-05-20","cited_by_count":0,"area":"alignment"},{"id":"2607.24484","title":"What do Reward Models Memorize?","created":"2026-07-27","cited_by_count":0,"area":"alignment"},{"id":"2608.22490","title":"Who Pays More for Safety? Measuring the Disparate Cost of Safety Alignment across Languages","created":"2026-08-23","cited_by_count":0,"area":"alignment"},{"id":"2609.18515","title":"Beyond Routine Compliance: Cunning Data Cultivates Safety Vigilance in Large Language Models","created":"2026-09-16","cited_by_count":0,"area":"alignment"}],"next_cursor":null}