Translation with Thought: Difficulty-Adaptive Reasoning via Reinforcement Learning for Multi-Domain Machine Translation
Yongshi Ye, Biao Fu, Chongxuan Huang, Yidong Chen, Xiaodong Shi
cs.CL, cs.AI
Submitted: 2026-07-31
Comments: 34 pages, 17 figures, and 21 tables. Accepted to ACL 2026
Code: https://github.com/hiyouga/LLaMA-Factoryhttps:
License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
Terminology
Sources
- Tower: An Open Multilingual Large Language Model for Translation-Related Tasks
- Evaluating o1-Like LLMs: Unlocking Reasoning for Translation through Comprehensive Analysis
- DeepSeek-V3 Technical Report
- MT-R1-Zero: Advancing LLM-based Machine Translation via R1-Zero-like Reinforcement Learning
- Gemma 2: Improving Open Language Models at a Practical Size
- The Llama 3 Herd of Models
- DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning
- Test-Time Scaling of Reasoning Models for Machine Translation
- New Trends for Modern Machine Translation with Large Reasoning Models
- R1-T1: Fully Incentivizing Translation Capability in LLMs via Reasoning Learning
- GPT-4o System Card
- OpenAI o1 System Card
- Tower+: Bridging Generality and Translation Specialization in Multilingual LLMs
- Proximal Policy Optimization Algorithms
- DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models
- DRT: Deep Reasoning Translation via Long Chain-of-Thought
- DeepTrans: Deep Reasoning Translation via Reinforcement Learning
- ExTrans: Multilingual Deep Reasoning Translation via Exemplar-Enhanced Reinforcement Learning
- Qwen2.5 Technical Report
- SSR-Zero: Simple Self-Rewarding Reinforcement Learning for 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