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

arXiv: https://arxiv.org/abs/2608.03077 · HTML: https://mlsanity.com/paper/2608.03077/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Placed in RL training of language and agent models, one of 15 directions in Deep reinforcement learning methods.
- Builds on 38 of its 54 references that are in the map.
- First posted on arXiv 4 Aug 2026.

## Placed in

- Deep reinforcement learning methods / [RL training of language and agent models](https://mlsanity.com/deeprl/rl-training-of-language-and-agent-models/)

## Builds on (most cited first, 30 of 38)

- [Efficient Memory Management for Large Language Model Serving with PagedAttention](https://mlsanity.com/paper/2309.06180/) (2023)
- [Let's Verify Step by Step](https://mlsanity.com/paper/2305.20050/) (2023)
- [HybridFlow: A Flexible and Efficient RLHF Framework](https://mlsanity.com/paper/2409.19256/) (2024)
- [A Call for Clarity in Reporting BLEU Scores](https://mlsanity.com/paper/1804.08771/) (2018)
- [LlamaFactory: Unified Efficient Fine-Tuning of 100+ Language Models](https://mlsanity.com/paper/2403.13372/) (2024)
- [COMET: A Neural Framework for MT Evaluation](https://mlsanity.com/paper/2009.09025/) (2020)
- [Math-Shepherd: Verify and Reinforce LLMs Step-by-step without Human Annotations](https://mlsanity.com/paper/2312.08935/) (2023)
- [Improve Mathematical Reasoning in Language Models by Automated Process Supervision](https://mlsanity.com/paper/2406.06592/) (2024)
- [Contrastive Preference Optimization: Pushing the Boundaries of LLM Performance in Machine Translation](https://mlsanity.com/paper/2401.08417/) (2024)
- [Experts, Errors, and Context: A Large-Scale Study of Human Evaluation for Machine Translation](https://mlsanity.com/paper/2104.14478/) (2021)
- [Step-DPO: Step-wise Preference Optimization for Long-chain Reasoning of LLMs](https://mlsanity.com/paper/2406.18629/) (2024)
- [LEVER: Learning to Verify Language-to-Code Generation with Execution](https://mlsanity.com/paper/2302.08468/) (2023)
- [Making Large Language Models Better Reasoners with Step-Aware Verifier](https://mlsanity.com/paper/2206.02336/) (2022)
- [Tower: An Open Multilingual Large Language Model for Translation-Related Tasks](https://mlsanity.com/paper/2402.17733/) (2024)
- [Unsupervised Domain Clusters in Pretrained Language Models](https://mlsanity.com/paper/2004.02105/) (2020)
- [GEMBA-MQM: Detecting Translation Quality Error Spans with GPT-4](https://mlsanity.com/paper/2310.13988/) (2023)
- [Has Machine Translation Achieved Human Parity? A Case for Document-level Evaluation](https://mlsanity.com/paper/1808.07048/) (2018)
- [BlonDe: An Automatic Evaluation Metric for Document-level Machine Translation](https://mlsanity.com/paper/2103.11878/) (2021)
- [Benchmarking Machine Translation with Cultural Awareness](https://mlsanity.com/paper/2305.14328/) (2023)
- [MT-R1-Zero: Advancing LLM-based Machine Translation via R1-Zero-like Reinforcement Learning](https://mlsanity.com/paper/2504.10160/) (2025)
- [Domain Adaptation and Multi-Domain Adaptation for Neural Machine Translation: A Survey](https://mlsanity.com/paper/2104.06951/) (2021)
- [Fine-tuning Large Language Models for Domain-specific Machine Translation](https://mlsanity.com/paper/2402.15061/) (2024)
- [Tower+: Bridging Generality and Translation Specialization in Multilingual LLMs](https://mlsanity.com/paper/2506.17080/) (2025)
- [TEaR: Improving LLM-based Machine Translation with Systematic Self-Refinement](https://mlsanity.com/paper/2402.16379/) (2024)
- [Translating Step-by-Step: Decomposing the Translation Process for Improved Translation Quality of Long-Form Texts](https://mlsanity.com/paper/2409.06790/) (2024)
- [DRT: Deep Reasoning Translation via Long Chain-of-Thought](https://mlsanity.com/paper/2412.17498/) (2024)
- [TasTe: Teaching Large Language Models to Translate through Self-Reflection](https://mlsanity.com/paper/2406.08434/) (2024)
- [Findings of the WMT 2023 Shared Task on Discourse-Level Literary Translation: A Fresh Orb in the Cosmos of LLMs](https://mlsanity.com/paper/2311.03127/) (2023)
- [Guiding Large Language Models to Post-Edit Machine Translation with Error Annotations](https://mlsanity.com/paper/2404.07851/) (2024)
- [DUAL-REFLECT: Enhancing Large Language Models for Reflective Translation through Dual Learning Feedback Mechanisms](https://mlsanity.com/paper/2406.07232/) (2024)

## Abstract (arXiv)

Multi-domain machine translation (MDMT) requires more than fluent generation: it demands domain-sensitive translation decisions such as domain disambiguation, terminology control, and stylistic adaptation. Large reasoning models (LRMs) make such decisions explicit through intermediate translation steps, but our analysis across 15 domains and four translation directions shows that this explicit reasoning is double-edged: it improves long-form and high-difficulty translation, yet often drifts in terminology-intensive and stylistically constrained settings. We trace this failure to a credit-assignment bottleneck: existing methods optimize final outputs or coarse trajectories, but cannot identify which translation steps actually help the final translation. To address this, we propose PAMT, a process-aligned training framework that combines cold-start domain-aware Long-CoT supervision with reinforcement learning. PAMT uses sequence-level format and outcome rewards for the final translation, together with a step-level process reward that measures how much each explicit translation step increases the likelihood of the reference translation. Across two backbones, PAMT improves over base models, outperforms MT-specialized baselines on average, and remains competitive with strong LLMs/LRMs across in-domain, OOD, and multilingual settings.