AIBullisharXiv – CS AI · 18h ago6/10
🧠
Rewrite to Translate, Translate to Reward: Reinforcement Learning for Source Rewriting in Machine Translation
Researchers introduce RLSR, a reinforcement learning framework that trains smaller language models to rewrite source text for improved machine translation without manual prompt tuning. The approach achieves competitive performance with larger models across six MT systems and 16 language pairs, demonstrating that RL-optimized 4B parameter models can match capabilities of 235B parameter prompt-based systems.