Far Out: Evaluating Language Models on Slang in Australian and Indian English

TL;DR

This paper evaluates how well state-of-the-art language models understand slang in Indian and Australian English, revealing performance gaps and differences across datasets and tasks, especially in non-standard language varieties.

Contribution

It introduces two new slang datasets for Indian and Australian English and systematically assesses models' abilities across multiple tasks and datasets.

Findings

Models perform better on target word selection than prediction tasks.

Models show higher accuracy on web-sourced data compared to synthetic data.

Indian English slang tasks outperform Australian English in model accuracy.

Abstract

Language models exhibit systematic performance gaps when processing text in non-standard language varieties, yet their ability to comprehend variety-specific slang remains underexplored for several languages. We present a comprehensive evaluation of slang awareness in Indian English (en-IN) and Australian English (en-AU) across seven state-of-the-art language models. We construct two complementary datasets: WEB, containing 377 web-sourced usage examples from Urban Dictionary, and GEN, featuring 1,492 synthetically generated usages of these slang terms, across diverse scenarios. We assess language models on three tasks: target word prediction (TWP), guided target word prediction (TWP$^*$) and target word selection (TWS). Our results reveal four key findings: (1) Higher average model performance TWS versus TWP and TWP$^*$, with average accuracy score increasing from 0.03 to 0.49 respectively (2) Stronger average model performance on WEB versus GEN datasets, with average similarity score increasing by 0.03 and 0.05 across TWP and TWP$^*$ tasks respectively (3) en-IN tasks outperform en-AU when averaged across all models and datasets, with TWS demonstrating the largest disparity, increasing average accuracy from 0.44 to 0.54. These findings underscore fundamental asymmetries between generative and discriminative competencies for variety-specific language, particularly in the context of slang expressions despite being in a technologically rich language such as English.