Large Language Models for Czech Aspect-Based Sentiment Analysis

TL;DR

This paper evaluates 19 large language models for Czech aspect-based sentiment analysis, revealing that fine-tuned domain-specific models outperform general-purpose LLMs in zero-shot and few-shot settings, with fine-tuned LLMs achieving state-of-the-art results.

Contribution

It provides a comprehensive comparison of LLMs for Czech ABSA, analyzing factors affecting performance and highlighting key challenges in aspect term prediction.

Findings

Fine-tuned domain-specific models outperform general-purpose LLMs in zero-shot and few-shot scenarios.

Fine-tuned LLMs achieve state-of-the-art results in Czech ABSA.

Performance is influenced by multilingualism, model size, and recency.

Abstract

Aspect-based sentiment analysis (ABSA) is a fine-grained sentiment analysis task that aims to identify sentiment toward specific aspects of an entity. While large language models (LLMs) have shown strong performance in various natural language processing (NLP) tasks, their capabilities for Czech ABSA remain largely unexplored. In this work, we conduct a comprehensive evaluation of 19 LLMs of varying sizes and architectures on Czech ABSA, comparing their performance in zero-shot, few-shot, and fine-tuning scenarios. Our results show that small domain-specific models fine-tuned for ABSA outperform general-purpose LLMs in zero-shot and few-shot settings, while fine-tuned LLMs achieve state-of-the-art results. We analyze how factors such as multilingualism, model size, and recency influence performance and present an error analysis highlighting key challenges, particularly in aspect term prediction. Our findings provide insights into the suitability of LLMs for Czech ABSA and offer guidance for future research in this area.