LLaMA-Based Models for Aspect-Based Sentiment Analysis
By: Jakub Šmíd, Pavel Přibáň, Pavel Král
Potential Business Impact:
Makes computers understand feelings about many things.
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 fine-tuned 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 state-of-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.
Similar Papers
Large Language Models for Czech Aspect-Based Sentiment Analysis
Computation and Language
Helps computers understand feelings about specific things.
LACA: Improving Cross-lingual Aspect-Based Sentiment Analysis with LLM Data Augmentation
Computation and Language
Lets computers understand feelings in any language.
Advancing Cross-lingual Aspect-Based Sentiment Analysis with LLMs and Constrained Decoding for Sequence-to-Sequence Models
Computation and Language
Helps computers understand opinions in any language.