2 papers
cs.CL2026
The Price of Reasoning: Cost-Quality Tradeoffs in Reinforcement Learning for Neural Machine Translation
Michael Jungo, Aixiu An
Reinforcement learning with verifiable rewards (RLVR) has been established as a viable paradigm for the post-training of Large Language Models (LLMs), including downstream tasks, s…
cs.CL2026
Reasoning Before Translation: Enhancing Legal Machine Translation with Structured Reasoning
Aixiu An, Michael Jungo, Eloi Eynard +4
Neural machine translation (NMT) in the legal domain is a linguistically and conceptually demanding task, primarily due to the complexity of legal language and the high level of pr…