Fine-tuning llama-2 and few-shot learning for ABSA

Li Wang; Xin Zeng; Long Zhou

doi:10.1117/12.3030995

19 July 2024 Fine-tuning llama-2 and few-shot learning for ABSA

Li Wang, Xin Zeng, Long Zhou

Proceedings Volume 13181, Third International Conference on Electronic Information Engineering, Big Data, and Computer Technology (EIBDCT 2024); 1318187 (2024) https://doi.org/10.1117/12.3030995
Event: Third International Conference on Electronic Information Engineering, Big Data, and Computer Technology (EIBDCT 2024), 2024, Beijing, China

Abstract

The Llama-2 model has demonstrated excellent performance in various research fields and can be adapted to specific tasks through fine-tuning techniques. This paper focuses on exploring the application of Llama-2 in aspect-based sentiment analysis (ABSA), specifically focusing on the joint tasks of aspect term extraction and polarity classification. We propose a few-shot ABSA method based on fine-tuning Llama-2. We discuss the impact of simple and complex training data instructions on model performance and find that their influence is minimal. Additionally, we investigate the performance of the fine-tuned model when using different numbers of context prompts during inference. We find that the fine-tuned Llama-2, combined with few-shot context prompts, performs well and can consistently output JSON format, achieving a maximum F1 score of 69.5%, which is a 3.8% improvement compared to GPT-3.5. Results analysis indicates that finetuning helps reduce false positives, improve model sensitivity, and specificity.

(2024) Published by SPIE. Downloading of the abstract is permitted for personal use only.

Citation Download Citation

Li Wang, Xin Zeng, and Long Zhou "Fine-tuning llama-2 and few-shot learning for ABSA", Proc. SPIE 13181, Third International Conference on Electronic Information Engineering, Big Data, and Computer Technology (EIBDCT 2024), 1318187 (19 July 2024); https://doi.org/10.1117/12.3030995

ACCESS THE FULL ARTICLE

INSTITUTIONAL
Select your institution to access the SPIE Digital Library.

SELECT YOUR INSTITUTION

PERSONAL
Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.

PERSONAL SIGN IN

No SPIE Account? Create one

PURCHASE THIS CONTENT

SUBSCRIBE TO DIGITAL LIBRARY

50 downloads per 1-year subscription

Members: $195

Non-members: $335 ADD TO CART

25 downloads per 1 - year subscription

Members: $145

Non-members: $250 ADD TO CART

PURCHASE SINGLE ARTICLE

Includes PDF, HTML & Video, when available