{"total":16,"rows":[{"id":"2402.11525","title":"Advancing Translation Preference Modeling with RLHF: A Step Towards Cost-Effective Solution","created":"2024-02-18","cited_by_count":13,"area":"alignment"},{"id":"2409.17472","title":"Autoregressive Multi-trait Essay Scoring via Reinforcement Learning with Scoring-aware Multiple Rewards","created":"2024-09-26","cited_by_count":12,"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":"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":"2502.00634","title":"SimulPL: Aligning Human Preferences in Simultaneous Machine Translation","created":"2025-02-02","cited_by_count":7,"area":"alignment"},{"id":"2411.09073","title":"CHAI for LLMs: Improving Code-Mixed Translation in Large Language Models through Reinforcement Learning with AI Feedback","created":"2024-11-13","cited_by_count":5,"area":"alignment"},{"id":"2502.19941","title":"Alleviating Distribution Shift in Synthetic Data for Machine Translation Quality Estimation","created":"2025-02-27","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":"2412.08473","title":"Multi-perspective Alignment for Increasing Naturalness in Neural Machine Translation","created":"2024-12-11","cited_by_count":1,"area":"alignment"},{"id":"2608.27161","title":"STAR : Sentence Translation Alignment Rate for Document-to-Document Machine Translation","created":"2026-08-27","cited_by_count":1,"area":"alignment"},{"id":"2406.10203","title":"A Probability--Quality Trade-off in Aligned Language Models and its Relation to Sampling Adaptors","created":"2024-06-14","cited_by_count":0,"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":"2410.11410","title":"PMMT: Preference Alignment in Multilingual Machine Translation via LLM Distillation","created":"2024-10-15","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"}],"next_cursor":null}