Exploring Multilingual Probing in Large Language Models: A Cross-Language Analysis

TL;DR

This paper investigates how large language models perform across multiple languages, revealing disparities between high-resource and low-resource languages in probing accuracy, layer-wise trends, and representational similarities.

Contribution

It extends probing techniques to a multilingual setting, providing a comprehensive analysis of LLM behaviors across diverse languages and highlighting resource-based performance gaps.

Findings

High-resource languages outperform low-resource ones in probing accuracy.

Layer-wise accuracy trends differ between high-resource and low-resource languages.

High-resource languages show greater representational similarity than low-resource languages.

Abstract

Probing techniques for large language models (LLMs) have primarily focused on English, overlooking the vast majority of the world's languages. In this paper, we extend these probing methods to a multilingual context, investigating the behaviors of LLMs across diverse languages. We conduct experiments on several open-source LLM models, analyzing probing accuracy, trends across layers, and similarities between probing vectors for multiple languages. Our key findings reveal: (1) a consistent performance gap between high-resource and low-resource languages, with high-resource languages achieving significantly higher probing accuracy; (2) divergent layer-wise accuracy trends, where high-resource languages show substantial improvement in deeper layers similar to English; and (3) higher representational similarities among high-resource languages, with low-resource languages demonstrating lower similarities both among themselves and with high-resource languages. These results highlight significant disparities in LLMs' multilingual capabilities and emphasize the need for improved modeling of low-resource languages.