Multilingual Large Language Models Are Not (Yet) Code-Switchers
Document Type
Conference Proceeding
Publication Title
EMNLP 2023 - 2023 Conference on Empirical Methods in Natural Language Processing, Proceedings
Abstract
Multilingual Large Language Models (LLMs) have recently shown great capabilities in a wide range of tasks, exhibiting state-of-the-art performance through zero-shot or few-shot prompting methods. While there have been extensive studies on their abilities in monolingual tasks, the investigation of their potential in the context of code-switching (CSW), the practice of alternating languages within an utterance, remains relatively uncharted. In this paper, we provide a comprehensive empirical analysis of various multilingual LLMs, benchmarking their performance across four tasks: sentiment analysis, machine translation, summarization and word-level language identification. Our results indicate that despite multilingual LLMs exhibiting promising outcomes in certain tasks using zero or few-shot prompting, they still underperform in comparison to fine-tuned models of much smaller scales. We argue that current “multilingualism" in LLMs does not inherently imply proficiency with code-switching texts, calling for future research to bridge this discrepancy.
First Page
12567
Last Page
12582
Publication Date
1-1-2023
Recommended Citation
R. Zhang et al., "Multilingual Large Language Models Are Not (Yet) Code-Switchers," EMNLP 2023 - 2023 Conference on Empirical Methods in Natural Language Processing, Proceedings, pp. 12567 - 12582, Jan 2023.