LLM-as-an-Annotator: Training Lightweight Models with LLM-Annotated Examples for Aspect Sentiment Tuple Prediction

TL;DR

This paper presents LA-ABSA, a method that uses LLM-generated annotations to train lightweight models for aspect-based sentiment analysis, reducing annotation costs while maintaining competitive performance and energy efficiency.

Contribution

LA-ABSA introduces a novel approach leveraging LLM-generated annotations to effectively train lightweight ABSA models, especially in low-resource scenarios.

Findings

LA-ABSA outperforms previous augmentation strategies.

Achieves competitive performance with LLM prompting in low-resource settings.

Significantly reduces computational resources needed for training.

Abstract

Training models for Aspect-Based Sentiment Analysis (ABSA) tasks requires manually annotated data, which is expensive and time-consuming to obtain. This paper introduces LA-ABSA, a novel approach that leverages Large Language Model (LLM)-generated annotations to fine-tune lightweight models for complex ABSA tasks. We evaluate our approach on five datasets for Target Aspect Sentiment Detection (TASD) and Aspect Sentiment Quad Prediction (ASQP). Our approach outperformed previously reported augmentation strategies and achieved competitive performance with LLM-prompting in low-resource scenarios, while providing substantial energy efficiency benefits. For example, using 50 annotated examples for in-context learning (ICL) to guide the annotation of unlabeled data, LA-ABSA achieved an F1 score of 49.85 for ASQP on the SemEval Rest16 dataset, closely matching the performance of ICL prompting with Gemma-3-27B (51.10), while requiring significantly lower computational resources.