LLaMA-Based Models for Aspect-Based Sentiment Analysis
Proceedings of the 14th Workshop on Computational Approaches to Subjectivity, Sentiment, & Social Media Analysis (WASSA 2024) (2024)
Abstract
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.
Authors
BibTex
@inproceedings{smid-etal-2024-llama, title = "{LL}a{MA}-Based Models for Aspect-Based Sentiment Analysis", author = "{\v{S}}m{\'\i}d, Jakub and Priban, Pavel and Kral, Pavel", editor = "De Clercq, Orph{\'e}e and Barriere, Valentin and Barnes, Jeremy and Klinger, Roman and Sedoc, Jo{\~a}o and Tafreshi, Shabnam", booktitle = "Proceedings of the 14th Workshop on Computational Approaches to Subjectivity, Sentiment, {\&} Social Media Analysis", month = aug, year = "2024", address = "Bangkok, Thailand", publisher = "Association for Computational Linguistics", url = "https://aclanthology.org/2024.wassa-1.6", pages = "63--70", abstract = "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.", }
