MasalBench: A Benchmark for Contextual and Cross-Cultural Understanding of Persian Proverbs in LLMs

TL;DR

MasalBench is a new benchmark designed to evaluate how well multilingual LLMs understand Persian proverbs in context and across cultures, revealing strengths in proverb recognition but limitations in cultural and analogical reasoning.

Contribution

Introduces MasalBench, the first comprehensive benchmark for assessing LLMs' understanding of Persian proverbs and cross-cultural analogies in a low-resource language.

Findings

LLMs perform above 0.90 in identifying Persian proverbs in context

Performance drops to 0.79 in identifying English equivalents of Persian proverbs

Current LLMs show limitations in cultural knowledge and analogical reasoning

Abstract

In recent years, multilingual Large Language Models (LLMs) have become an inseparable part of daily life, making it crucial for them to master the rules of conversational language in order to communicate effectively with users. While previous work has evaluated LLMs' understanding of figurative language in high-resource languages, their performance in low-resource languages remains underexplored. In this paper, we introduce MasalBench, a comprehensive benchmark for assessing LLMs' contextual and cross-cultural understanding of Persian proverbs, which are a key component of conversation in this low-resource language. We evaluate eight state-of-the-art LLMs on MasalBench and find that they perform well in identifying Persian proverbs in context, achieving accuracies above 0.90. However, their performance drops considerably when tasked with identifying equivalent English proverbs, with the best model achieving 0.79 accuracy. Our findings highlight the limitations of current LLMs in cultural knowledge and analogical reasoning, and they provide a framework for assessing cross-cultural understanding in other low-resource languages. MasalBench is available at https://github.com/kalhorghazal/MasalBench.