Saved in:
Bibliographic Details
Main Authors: Gupta, Ayushman, Bhogal, Akhil, Ghosh, Kripabandhu
Format: Preprint
Published: 2024
Subjects:
Online Access:https://arxiv.org/abs/2410.11079
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866909349602918400
author Gupta, Ayushman
Bhogal, Akhil
Ghosh, Kripabandhu
author_facet Gupta, Ayushman
Bhogal, Akhil
Ghosh, Kripabandhu
contents Multilingual Large Language Models (LLMs) have demonstrated exceptional performance in Machine Translation (MT) tasks. However, their MT abilities in the context of code-switching (the practice of mixing two or more languages in an utterance) remain under-explored. In this paper, we introduce Rule-Based Prompting, a novel prompting technique to generate code-mixed sentences. We measure and compare the code-mixed MT abilities of 3 popular multilingual LLMs: GPT-3.5-turbo, GPT-4, and Gemini Pro across five language pairs: English-{Hindi, Bengali, Gujarati, French, Spanish} using $k$-shot prompting ($k\in\{0, 1, 10, 20\}$) and Rule-Based Prompting. Our findings suggest that though $k$-shot prompting often leads to the best results, Rule-Based prompting shows promise in generating unique code-mixed sentences that vary in their style of code-mixing. We also use $k$-shot prompting to gauge the code-mixed to English translation abilities of multilingual LLMs. For this purpose, we create a gold-standard code-mixed dataset spanning five language pairs: English-{Hindi, Bengali, Gujarati, French, Spanish}. As a real-world application of our work, we create a code-mixed chatbot.
format Preprint
id arxiv_https___arxiv_org_abs_2410_11079
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Code-Mixer Ya Nahi: Novel Approaches to Measuring Multilingual LLMs' Code-Mixing Capabilities
Gupta, Ayushman
Bhogal, Akhil
Ghosh, Kripabandhu
Computation and Language
Artificial Intelligence
Multilingual Large Language Models (LLMs) have demonstrated exceptional performance in Machine Translation (MT) tasks. However, their MT abilities in the context of code-switching (the practice of mixing two or more languages in an utterance) remain under-explored. In this paper, we introduce Rule-Based Prompting, a novel prompting technique to generate code-mixed sentences. We measure and compare the code-mixed MT abilities of 3 popular multilingual LLMs: GPT-3.5-turbo, GPT-4, and Gemini Pro across five language pairs: English-{Hindi, Bengali, Gujarati, French, Spanish} using $k$-shot prompting ($k\in\{0, 1, 10, 20\}$) and Rule-Based Prompting. Our findings suggest that though $k$-shot prompting often leads to the best results, Rule-Based prompting shows promise in generating unique code-mixed sentences that vary in their style of code-mixing. We also use $k$-shot prompting to gauge the code-mixed to English translation abilities of multilingual LLMs. For this purpose, we create a gold-standard code-mixed dataset spanning five language pairs: English-{Hindi, Bengali, Gujarati, French, Spanish}. As a real-world application of our work, we create a code-mixed chatbot.
title Code-Mixer Ya Nahi: Novel Approaches to Measuring Multilingual LLMs' Code-Mixing Capabilities
topic Computation and Language
Artificial Intelligence
url https://arxiv.org/abs/2410.11079