Multilingual Arbitrage: Optimizing Data Pools to Accelerate Multilingual Progress
Paper • 2408.14960 • Published
Aya
-
-
RLHF Can Speak Many Languages: Unlocking Multilingual Preference Optimization for LLMs
Paper • 2407.02552 • Published • 4 -
The Multilingual Alignment Prism: Aligning Global and Local Preferences to Reduce Harm
Paper • 2406.18682 • Published -
Mix Data or Merge Models? Optimizing for Diverse Multi-Task Learning
Paper • 2410.10801 • Published • 3