LLaMA-Based Models for Aspect-Based Sentiment Analysis
The result's identifiers
Result code in IS VaVaI
<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F49777513%3A23520%2F24%3A43972808" target="_blank" >RIV/49777513:23520/24:43972808 - isvavai.cz</a>
Result on the web
<a href="https://aclanthology.org/2024.wassa-1.6/" target="_blank" >https://aclanthology.org/2024.wassa-1.6/</a>
DOI - Digital Object Identifier
<a href="http://dx.doi.org/10.18653/v1/2024.wassa-1.6" target="_blank" >10.18653/v1/2024.wassa-1.6</a>
Alternative languages
Result language
angličtina
Original language name
LLaMA-Based Models for Aspect-Based Sentiment Analysis
Original language description
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.
Czech name
—
Czech description
—
Classification
Type
D - Article in proceedings
CEP classification
—
OECD FORD branch
10201 - Computer sciences, information science, bioinformathics (hardware development to be 2.2, social aspect to be 5.8)
Result continuities
Project
—
Continuities
S - Specificky vyzkum na vysokych skolach
Others
Publication year
2024
Confidentiality
S - Úplné a pravdivé údaje o projektu nepodléhají ochraně podle zvláštních právních předpisů
Data specific for result type
Article name in the collection
Proceedings of the 14th Workshop on Computational Approaches to Subjectivity, Sentiment, & Social Media Analysis
ISBN
979-8-89176-156-8
ISSN
—
e-ISSN
—
Number of pages
8
Pages from-to
63-70
Publisher name
Association for Computational Linguistics
Place of publication
Kerrville
Event location
Bangkok, Thailand
Event date
Aug 15, 2024
Type of event by nationality
WRD - Celosvětová akce
UT code for WoS article
—