Can Large Language Models Handle Discourse Particles? A Case Study of Colloquial Malay

2026-05-27

AI Summary

This study addresses the lack of systematic evaluation of pragmatic understanding of discourse particles in low-resource Southeast Asian languages—particularly colloquial Malay—by large language models (LLMs). The authors introduce MalayPrag, the first benchmark specifically designed for assessing LLMs’ comprehension of colloquial Malay discourse particles, and propose a linguistically grounded five-dimensional pragmatic attribute framework to structurally model the affective and intentional functions of these particles. Through prompt-based experiments, ten prominent LLMs are systematically evaluated across three prediction tasks. Results reveal that current models struggle to accurately associate discourse particles with their pragmatic functions; however, incorporating the proposed five-dimensional framework substantially improves model performance. This work establishes a novel paradigm for evaluating pragmatic competence in low-resource languages.

Abstract

Discourse particles, such as \textit{well} and \textit{kind of}, are crucial components that enable LLMs to ``speak'' more like humans. They are used to convey emotions, intentions, and interpersonal meanings. However, existing studies have not yet built a comprehensive understanding of LLMs' capabilities in handling discourse particles. Moreover, the limited number of studies focuses primarily on high-resource languages such as English, with little attention paid to Southeast Asian languages. In this paper, we (1) propose \textsc{MalayPrag}, a benchmark designed to systematically evaluate and analyze LLMs' capabilities in handling discourse particles in colloquial Malay; and (2) introduce five attributes that provide a linguistically grounded, unified framework for interpreting the pragmatic functions of discourse particles. Applying these two contributions, we prompt ten off-the-shelf LLMs to perform three prediction tasks. The experimental results reveal substantial challenges for current LLMs in accurately connecting discourse particles with their pragmatic functions in Malay. The provision of the five attributes designed in this study is found to significantly improve these connections, highlighting the need for structured scaffolding for models' pragmatic competence.

Problem

• discourse particles
• large language models
• colloquial Malay
• pragmatic functions
• Southeast Asian languages

Innovation

• discourse particles
• MalayPrag
• pragmatic functions
• large language models
• colloquial Malay