neural-machine-translation-7f0e8317·1 events·first seen Aliases: Neural Machine Translation
A new arXiv preprint investigates whether quality gains from reinforcement learning with verifiable rewards (RLVR) in neural machine translation stem from the reasoning trace itself or from the training paradigm more broadly. Experiments show that including reasoning during inference specifically improves translation quality, while omitting it during training has less impact. The paper quantifies the cost-quality tradeoff introduced by longer reasoning outputs, finding that better translations come at meaningful computational expense.