Decoder-only large language models (LLMs) excel in high-resource languages
across various tasks through few-shot or even zero-shot in-context learning
(ICL). However, their performance often does not transfer well to low-resource
languages, especially those written in non-Latin scripts. Inspired by recent
work that leverages transliteration in encoder-only models, we investigate
whether transliteration is also effective in improving LLMs' performance for
low-resource languages written in non-Latin scripts. To this end, we propose
three prompt templates, where the target-language text is represented in (1)
its original script, (2) Latin script, or (3) both. We apply these methods to
several representative LLMs of different sizes on various tasks including text
classification and sequential labeling. Our findings show that the
effectiveness of transliteration varies by task type and model size. For
instance, all models benefit from transliterations for sequential labeling
(with increases of up to 25%).

研究发现，通过使用转写技术，可以提高非拉丁脚本的低资源语言中解码器优化的大型语言模型（LLMs）在顺序标注任务中的性能。

探索音译在上下文学习中的作用，针对非拉丁文字书写的低资源语言

Exploring the Role of Transliteration in In-Context Learning for  Low-resource Languages Written in Non-Latin Scripts

Existing zero-shot cross-lingual NER approaches require substantial prior
knowledge of the target language, which is impractical for low-resource
languages. In this paper, we propose a novel approach to NER using phonemic
representation based on the International Phonetic Alphabet (IPA) to bridge the
gap between representations of different languages. Our experiments show that
our method significantly outperforms baseline models in extremely low-resource
languages, with the highest average F-1 score (46.38%) and lowest standard
deviation (12.67), particularly demonstrating its robustness with non-Latin
scripts.

提出一种基于国际音标的音素表示的零样本跨语言命名实体识别方法，可有效提高低资源语言的性能，并在非拉丁文脚本上表现出很强的鲁棒性。

使用音素表示进行低资源语言的零射击跨语言命名实体识别

Zero-Shot Cross-Lingual NER Using Phonemic Representations for  Low-Resource Languages

This study addresses the challenge of extending Large Language Models (LLMs)
to non-English languages, specifically those using non-Latin scripts. We
propose an innovative approach that utilizes the romanized form of text as an
interface for LLMs, hypothesizing that its frequent informal use and shared
tokens with English enhance cross-lingual alignment. Focusing on Hindi, we
demonstrate through Hindi-to-English translation and sentiment analysis tasks
that romanized text not only significantly improves inference efficiency due to
its lower fertility compared to native text but also achieves competitive
performance with limited pre-training. Additionally, our novel multi-script
prompting approach, which combines romanized and native texts, shows promise in
further enhancing task performance. These findings suggest the potential of
romanization in bridging the language gap for LLM applications, with future
work aimed at expanding this approach to more languages and tasks.

本研究通过使用罗马化文本作为 LLMs 的界面来解决将大型语言模型扩展到非英语语言（尤其是使用非拉丁文字的语言）的挑战，并通过印地语到英语翻译和情感分析任务展示了罗马化文本的潜力，既提高了推理效率，又在有限的预训练情况下取得了竞争性的性能，同时将罗马化文本与原生文本结合的多脚本提示方法也显示出了提高任务性能的潜力。这些发现表明罗马化在弥合 LLM 应用中的语言障碍方面具有潜力，未来的工作将致力于将这种方法扩展到更多的语言和任务。