Going Beyond Word Matching: Syntax Improves In-context Example Selection for Machine Translation

arXiv:2403.19285v1 Announce Type: new
Abstract: In-context learning (ICL) is the trending prompting strategy in the era of large language models (LLMs), where a few examples are demonstrated to evoke LLMs' power for a given task. How to select informative examples remains an open issue. Previous works on in-context example selection for machine translation (MT) focus on superficial word-level features while ignoring deep syntax-level knowledge. In this paper, we propose a syntax-based in-context example selection method for MT, by computing the …

abstract arxiv beyond context cs.cl example examples in-context learning issue language language models large language large language models llms machine machine translation power prompting strategy syntax translation trending type word