PAMT: Process-Aligned Reinforcement Learning for Multi-Domain Machine Translation

arXiv:2608.03077 · cs.CL · Submitted 2026-08-04 · Read on arXiv

Yongshi Ye, Biao Fu, Chongxuan Huang, Yidong Chen, Xiaodong Shi

cs.CL

Submitted: 2026-08-04

Comments: 23 pages, 10 figures, and 18 tables

Code: https://github.com/hiyouga/LLaMA-Factoryhttps:

License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/

Terminology

• GRPO — 16× in this paper · explained in 6 episodes
• Credit assignment — 11× in this paper · explained in 3 episodes
• Reinforcement Learning — 11× in this paper · explained in 4 episodes
• Accuracy — 9× in this paper · explained in 1 episode
• Benchmark — 8× in this paper · explained in 2 episodes
• Trace — 8× in this paper · explained in 2 episodes
• Papers — 7× in this paper · explained in 3 episodes
• Fine-Tuning — 5× in this paper · explained in 5 episodes
• Generalization — 4× in this paper · explained in 14 episodes
• Ablation — 3× in this paper · explained in 1 episode
• Adam — 3× in this paper · explained in 3 episodes
• Benchmarking — 2× in this paper · explained in 4 episodes
• Calibration — 2× in this paper · explained in 9 episodes
• Clarity — 2× in this paper · explained in 3 episodes
• Coherence — 2× in this paper · explained in 2 episodes
• Consistency — 2× in this paper · explained in 3 episodes
• Distillation — 2× in this paper · explained in 2 episodes
• Domain Shift — 2× in this paper · explained in 7 episodes
• Empirical Methods in Natural Language Processing — 2× in this paper
• Evaluation Protocol — 2× in this paper · explained in 2 episodes
• Hallucination — 2× in this paper · explained in 4 episodes
• KL Regularization — 2× in this paper · explained in 2 episodes
• Multidimensional Quality Metrics — 2× in this paper
• Overfitting — 2× in this paper · explained in 2 episodes
• Regularization — 2× in this paper · explained in 3 episodes
• Ablation Study — 1× in this paper · explained in 3 episodes
• Augmentation — 1× in this paper · explained in 2 episodes
• Chain-of-Thought (CoT) — 1× in this paper · explained in 5 episodes
• Contextual Understanding — 1× in this paper · explained in 3 episodes
• Cross-Domain Generalization — 1× in this paper · explained in 3 episodes
• Domain Adaptation — 1× in this paper · explained in 5 episodes
• Feedback Mechanisms — 1× in this paper · explained in 2 episodes
• Frozen model — 1× in this paper · explained in 3 episodes
• GRPO Objective — 1× in this paper · explained in 2 episodes
• Localization — 1× in this paper · explained in 2 episodes
• Reasoning Traces — 1× in this paper · explained in 4 episodes
• Reinforcement Learning (RL) — 1× in this paper · explained in 26 episodes
• Robustness — 1× in this paper · explained in 6 episodes
• Verifier — 1× in this paper · explained in 2 episodes

Sources

• DeepSeek-V3 Technical Report
• Tower: An Open Multilingual Large Language Model for Translation-Related Tasks
• MT-RewardTree: A Comprehensive Framework for Advancing LLM-Based Machine Translation via Reward Modeling
• DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning
• R1-T1: Fully Incentivizing Translation Capability in LLMs via Reasoning Learning
• Step-DPO: Step-wise Preference Optimization for Long-chain Reasoning of LLMs
• TAT-R1: Terminology-Aware Translation with Reinforcement Learning and Word Alignment
• Let's Verify Step by Step
• Improve Mathematical Reasoning in Language Models by Automated Process Supervision
• Tower+: Bridging Generality and Translation Specialization in Multilingual LLMs
• DMDTEval: An Evaluation and Analysis of LLMs on Disambiguation in Multi-domain Translation
• GPT-4o System Card
• DRT: Deep Reasoning Translation via Long Chain-of-Thought
• DeepTrans: Deep Reasoning Translation via Reinforcement Learning
• SSR-Zero: Simple Self-Rewarding Reinforcement Learning for Machine Translation
• ExTrans: Multilingual Deep Reasoning Translation via Exemplar-Enhanced Reinforcement Learning
• Fine-tuning Large Language Models for Domain-specific Machine Translation

Related papers

• Exploring Solution Divergence and Its Effect on Large Language Model Problem Solving
• Ishigaki-IDS-Bench: A Benchmark for Generating Information Delivery Specification from BIM Information Requirements
• Subliminal Steering: Stronger Encoding of Hidden Signals
• MedStruct-S: A Benchmark for Key Discovery, Key-Conditioned QA and Semi-Structured Extraction from OCR Clinical Reports
• The End of Transformers? On Challenging Attention and the Rise of Sub-Quadratic Architectures
• Untangling the Mechanisms of Misleading Context in Medical Question Answering