I’m very excited to share our new work on machine translation evaluation with large language models. We find that the reference can significantly enhance the performance, while the source can have negative effects. Paper: arxiv.org/pdf/2401.06568… Code: github.com/xuuHuang/lost_…

🎉 Excited to share “Generalizing from Short to Long: Effective Data Synthesis for Long-Context Instruction Tuning” 📄 (arxiv.org/pdf/2502.15592) We propose "context synthesis": instead of generating instructions from long texts, we synthesize contexts for instructions—drawing

📢 Happy to bring our new paper! 🤩 > Non-En can exceed En in reasoning tasks > Ensembling 4+ langs in inference can bring about 10% more theoretical gain than En > Gain robust to lang choice and translation quality Paper: huggingface.co/papers/2504.11… Repo: github.com/CONE-MT/multil…