Label-Consistent Data Generation for Aspect-Based Sentiment Analysis Using LLM Agents

Mohammad H. A. Monfared, Lucie Flek, Akbar Karimi · Feb 18, 2026 · Citations: 0

Abstract

We propose an agentic data augmentation method for Aspect-Based Sentiment Analysis (ABSA) that uses iterative generation and verification to produce high quality synthetic training examples. To isolate the effect of agentic structure, we also develop a closely matched prompting-based baseline using the same model and instructions. Both methods are evaluated across three ABSA subtasks (Aspect Term Extraction (ATE), Aspect Sentiment Classification (ATSC), and Aspect Sentiment Pair Extraction (ASPE)), four SemEval datasets, and two encoder-decoder models: T5-Base and Tk-Instruct. Our results show that the agentic augmentation outperforms raw prompting in label preservation of the augmented data, especially when the tasks require aspect term generation. In addition, when combined with real data, agentic augmentation provides higher gains, consistently outperforming prompting-based generation. These benefits are most pronounced for T5-Base, while the more heavily pretrained Tk-Instruct exhibits smaller improvements. As a result, augmented data helps T5-Base achieve comparable performance with its counterpart.

Human Data Lens

Uses human feedback: No
Feedback types: None
Rater population: Unknown
Unit of annotation: Unknown
Expertise required: Coding

Evaluation Lens

Evaluation modes: Automatic Metrics
Agentic eval: None
Quality controls: Not reported
Confidence: 0.40
Flags: low_signal, possible_false_positive

Research Summary

Contribution Summary

We propose an agentic data augmentation method for Aspect-Based Sentiment Analysis (ABSA) that uses iterative generation and verification to produce high quality synthetic training examples.
To isolate the effect of agentic structure, we also develop a closely matched prompting-based baseline using the same model and instructions.
Both methods are evaluated across three ABSA subtasks (Aspect Term Extraction (ATE), Aspect Sentiment Classification (ATSC), and Aspect Sentiment Pair Extraction (ASPE)), four SemEval datasets, and two encoder-decoder models: T5-Base and Tk

Why It Matters For Eval

We propose an agentic data augmentation method for Aspect-Based Sentiment Analysis (ABSA) that uses iterative generation and verification to produce high quality synthetic training examples.
To isolate the effect of agentic structure, we also develop a closely matched prompting-based baseline using the same model and instructions.