作者位次 #2/7ACL 2026Poster· Natural Language Processing
One Pair Suffices: Unlocking Universal Zero-Shot Translation via Cross-Architecture Alignment
Hao Zong · Cong Hu Yuan · Chao Bei · Wentao Chen · Huan Liu · Kaiyu Huang · Degen Huang
摘要
Current paradigms for empowering Large Language Models (LLMs) with multilingual capabilities rely heavily on massive instruction tuning. We challenge this view, proposing that the barrier is topological alignment, not data quantity. We introduce Hybrid Cross-Alignment (HCA), fusing a frozen NLLB...