New paper alert! Could thinking multilingually empower LLM reasoning?
Exploring the potential for multilingualism in reasoning tasks, and finding it offers significant and robust advantages over English-only approaches.
📢 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: https://t.co/u2aTV9UBfc
Repo: https://t.co/36Fbikvn1S
We finally analyzed the possible reasons for the high but challenging upper bound:
> Language-difficulty match and key advantage languages can be found to help multilingual reasoning
> Minority correctness and model language biases makes the upper bound hard to achieve
(🧵3/3)
🚀Exciting new!
Introducing LLaMAX, a powerful LLM with enhanced translation performance across all 101 languages.
🔥 LLaMAX provides a better starting point for multilingual tasks and lots of analysis on the multilingual continual pre-training.
https://t.co/0RdwuA3k0v