Preprint
Aug 2026
OmniAlign: A Unified Multilingual Aligner for Word and Sentence Alignment
Surprisingly, later-stage supervised fine-tuning on short texts further improves alignment quality while retaining the long-context understanding acquired in earlier training, keeping the model robust on long-text word alignment.
Mengpeng Yang, Jingxu Yang, Chao Chen et al.
· 0 citations