{"total":18,"rows":[{"id":"2401.08417","title":"Contrastive Preference Optimization: Pushing the Boundaries of LLM Performance in Machine Translation","created":"2024-01-16","cited_by_count":394,"area":"alignment"},{"id":"2311.09336","title":"LLMRefine: Pinpointing and Refining Large Language Models via Fine-Grained Actionable Feedback","created":"2023-11-15","cited_by_count":39,"area":"alignment"},{"id":"2505.16637","title":"SSR-Zero: Simple Self-Rewarding Reinforcement Learning for Machine Translation","created":"2025-05-22","cited_by_count":13,"area":"alignment"},{"id":"2411.05986","title":"Fine-Grained Reward Optimization for Machine Translation using Error Severity Mappings","created":"2024-11-08","cited_by_count":11,"area":"alignment"},{"id":"2504.13630","title":"Remedy: Learning Machine Translation Evaluation from Human Preferences with Reward Modeling","created":"2025-04-18","cited_by_count":9,"area":"alignment"},{"id":"2410.07779","title":"Modeling User Preferences with Automatic Metrics: Creating a High-Quality Preference Dataset for Machine Translation","created":"2024-10-10","cited_by_count":8,"area":"alignment"},{"id":"2409.20059","title":"Is Preference Alignment Always the Best Option to Enhance LLM-Based Translation? An Empirical Analysis","created":"2024-09-30","cited_by_count":4,"area":"alignment"},{"id":"2510.13434","title":"$M^2PO$: Multi-Perspective Multi-Pair Preference Optimization for Machine Translation","created":"2025-10-15","cited_by_count":4,"area":"alignment"},{"id":"2603.13045","title":"Mending the Holes: Mitigating Reward Hacking in Reinforcement Learning for Multilingual Translation","created":"2026-03-13","cited_by_count":4,"area":"alignment"},{"id":"2410.02320","title":"Post-edits Are Preferences Too","created":"2024-10-03","cited_by_count":3,"area":"alignment"},{"id":"2501.13927","title":"CRPO: Confidence-Reward Driven Preference Optimization for Machine Translation","created":"2025-01-23","cited_by_count":3,"area":"alignment"},{"id":"2508.08550","title":"Fine-grained Video Dubbing Duration Alignment with Segment Supervised Preference Optimization","created":"2025-08-12","cited_by_count":3,"area":"alignment"},{"id":"2602.01068","title":"From Utterance to Vividity: Training Expressive Subtitle Translation LLM via Adaptive Local Preference Optimization","created":"2026-02-01","cited_by_count":1,"area":"alignment"},{"id":"2410.10228","title":"QE-EBM: Using Quality Estimators as Energy Loss for Machine Translation","created":"2024-10-14","cited_by_count":0,"area":"alignment"},{"id":"2507.22219","title":"RL from Teacher-Model Refinement: Gradual Imitation Learning for Machine Translation","created":"2025-07-29","cited_by_count":0,"area":"alignment"},{"id":"2602.08600","title":"Beyond Scalar Scores: Reinforcement Learning for Error-Aware Quality Estimation of Machine Translation","created":"2026-02-09","cited_by_count":0,"area":"alignment"},{"id":"2606.08011","title":"Rewrite to Translate, Translate to Reward: Reinforcement Learning for Source Rewriting in Machine Translation","created":"2026-06-06","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"}],"next_cursor":null}