LLaMA-Based Models for Aspect-Based Sentiment Analysis
Jakub Šmíd, Pavel Přibáň, Pavel Král · 2024
While large language models (LLMs) show promise for various tasks, their performance in compound aspect-based sentiment analysis (ABSA) tasks lags behind fine-tuned models.However, the potential of LLMs fine-tuned for ABSA remains unexplored.This paper examines the capabilities of open-source LLMs finetuned for ABSA, focusing on LLaMA-based models.We evaluate the performance across four tasks and eight English datasets, finding that the fine-tuned Orca 2 model surpasses stateof-the-art results in all tasks.However, all models struggle in zero-shot and few-shot scenarios compared to fully fine-tuned ones.Additionally, we conduct error analysis to identify challenges faced by fine-tuned models.