{"total":15,"rows":[{"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":"2603.00025","title":"TAB-PO: Preference Optimization with a Token-Level Adaptive Barrier for Token-Critical Structured Generation","created":"2026-02-03","cited_by_count":7,"area":"alignment"},{"id":"2604.01476","title":"From Rebound to Remedy: Understanding and Mitigating Reward Hacking via Representation Engineering","created":"2026-04-01","cited_by_count":7,"area":"alignment"},{"id":"2511.21050","title":"Breaking the Safety-Capability Tradeoff: Reinforcement Learning with Verifiable Rewards Maintains Safety Guardrails in LLMs","created":"2025-11-26","cited_by_count":3,"area":"alignment"},{"id":"2605.17602","title":"AutoRubric-T2I: Robust Rule-Based Reward Model for Text-to-Image Alignment","created":"2026-05-17","cited_by_count":3,"area":"alignment"},{"id":"2509.21798","title":"Evaluating and Improving Cultural Awareness of Reward Models for LLM Alignment","created":"2025-09-26","cited_by_count":2,"area":"alignment"},{"id":"2602.00426","title":"LLMs as High-Dimensional Nonlinear Autoregressive Models with Attention: Training, Alignment and Inference","created":"2026-01-31","cited_by_count":2,"area":"alignment"},{"id":"2607.03528","title":"Aligning Language Models with Selective Prediction","created":"2026-07-03","cited_by_count":2,"area":"alignment"},{"id":"2601.04411","title":"Rate or Fate? RLV$^\\varepsilon$R: Reinforcement Learning with Verifiable Noisy Rewards","created":"2026-01-07","cited_by_count":1,"area":"alignment"},{"id":"2605.04356","title":"Efficiently Aligning Language Models with Online Natural Language Feedback","created":"2026-05-05","cited_by_count":0,"area":"alignment"},{"id":"2608.15402","title":"Towards a theory of inference-time alignment with unknown rewards","created":"2026-08-15","cited_by_count":0,"area":"alignment"},{"id":"2609.01246","title":"Ready to Speak: Aligning LLMs for TTS-Friendly Text Generation","created":"2026-09-01","cited_by_count":0,"area":"alignment"},{"id":"2609.05111","title":"Unifying ICL, SFT, KL-Regularized RL Through a Bayesian Lens","created":"2026-09-04","cited_by_count":0,"area":"alignment"},{"id":"2609.33298","title":"Direct Hidden-State Alignment: Mapping and Controlling Preference Expression in LLMs","created":"2026-09-27","cited_by_count":0,"area":"alignment"},{"id":"2610.16866","title":"Efficient Resource-Shiftable RL Post-training with Generative Rewards","created":"2026-10-12","cited_by_count":0,"area":"alignment"}],"next_cursor":null}