Tag
This paper from Xiaomi introduces reference-free post-training for multilingual machine translation, applying GRPO with quality-estimation rewards to the MiLMMT-46-v0.1 SFT models, producing MiLMMT-46-v1.0 that improves translation across 46 languages and outperforms open and proprietary baselines.
This paper introduces MiLMMT-46-v1.0, a multilingual machine translation model improved via reference-free post-training with GRPO and checkpoint interpolation, surpassing strong open and proprietary baselines across 46 languages.
Proposes a two-stage cascaded framework for cost-aware LLM serving that clusters queries and routes them to cost-effective models, then escalates low-quality outputs to stronger models. Retains 97-99% of accuracy while reducing inference cost.
This paper proposes using Receiver Operating Characteristic (ROC) analysis to evaluate translation quality estimation (QE) systems, demonstrating that it offers actionable performance insights for business decision-making and is consistent with current methods.