Exploring large language models for the generation of synthetic training samples for aspect-based sentiment analysis in low resource settings

Download PDF
Open Webpage

Nils Constantin Hellwig, Jakob Fehle, Christian Wolff

Published: 2025, Last Modified: 06 May 2026Expert Syst. Appl. 2025EveryoneRevisionsBibTeXCC BY-SA 4.0
Abstract: Highlights•LLM-generated examples enhance performance in Aspect Category Detection (ACD).•Synthetic examples lead to an F1 score of 81.33 on the ACD task.•Llama-3-70B generated more linguistically diverse data than GPT-3.