Are LLMs Truly Multilingual? Exploring Zero-Shot Multilingual Capability of LLMs for Information Retrieval: An Italian Healthcare Use Case

TL;DR

This paper investigates the zero-shot multilingual capabilities of open-source LLMs in extracting information from Italian electronic health records, revealing performance limitations and variability across models and diseases.

Contribution

It provides a detailed experimental analysis of open-source multilingual LLMs' effectiveness in Italian healthcare information extraction, highlighting their current limitations.

Findings

Some LLMs struggle in zero-shot settings.

Performance varies significantly across models.

Generalization across diseases remains challenging.

Abstract

Large Language Models (LLMs) have become a key topic in AI and NLP, transforming sectors like healthcare, finance, education, and marketing by improving customer service, automating tasks, providing insights, improving diagnostics, and personalizing learning experiences. Information extraction from clinical records is a crucial task in digital healthcare. Although traditional NLP techniques have been used for this in the past, they often fall short due to the complexity, variability of clinical language, and high inner semantics in the free clinical text. Recently, Large Language Models (LLMs) have become a powerful tool for better understanding and generating human-like text, making them highly effective in this area. In this paper, we explore the ability of open-source multilingual LLMs to understand EHRs (Electronic Health Records) in Italian and help extract information from them in real-time. Our detailed experimental campaign on comorbidity extraction from EHR reveals that some LLMs struggle in zero-shot, on-premises settings, and others show significant variation in performance, struggling to generalize across various diseases when compared to native pattern matching and manual annotations.