LLaMA-Based Models for Aspect-Based Sentiment Analysis
About
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.
Jakub \v{S}m\'id, Pavel P\v{r}ib\'a\v{n}, Pavel Kr\'al• 2025
Related benchmarks
| Task | Dataset | Result | Rank | |
|---|---|---|---|---|
| Aspect Sentiment Quad Prediction | Rest15 | F1 Score52.29 | 93 | |
| Aspect Sentiment Quad Prediction | Rest16 | F1 Score60.82 | 93 | |
| Target Aspect Sentiment Detection | Rest15 | F1 Score70.49 | 63 | |
| Target Aspect Sentiment Detection | Rest16 | F1 Score78.82 | 42 |
Showing 4 of 4 rows