OFA: A Framework of Initializing Unseen Subword Embeddings for Efficient Large-scale Multilingual Continued Pretraining Paper • 2311.08849 • Published Nov 15, 2023 • 6
Refusal Direction is Universal Across Safety-Aligned Languages Paper • 2505.17306 • Published May 22 • 2
Language Mixing in Reasoning Language Models: Patterns, Impact, and Internal Causes Paper • 2505.14815 • Published May 20 • 2
Lost in Multilinguality: Dissecting Cross-lingual Factual Inconsistency in Transformer Language Models Paper • 2504.04264 • Published Apr 5 • 2