一作ACL 2026Poster· Natural Language Processing
How to Improve LLM s’ Performance on Specific Languages: A Perspective on LLM -Derived Language Similarity
Xinhe Shi · Qingcheng Zeng · Weihao Xuan · Linchao Zhu
摘要
Large language models (LLMs) exhibit uneven performance across languages. In language-specific applications, practitioners often rely on target-language corpora or cross-lingual transfer to achieve better performance. However, traditional linguistic typology, commonly used as a transfer language...