DS2-ABSA: Dual-Stream Data Synthesis with Label Refinement for Few-Shot Aspect-Based Sentiment Analysis

Recently developed large language models (LLMs) have presented promising new avenues to address data scarcity in low-resource scenarios. In few-shot aspect-based sentiment analysis (ABSA), previous efforts have explored data augmentation techniques, which prompt LLMs to generate new samples by modifying existing ones. However, these methods fail to produce adequately diverse data, impairing their effectiveness. Besides, some studies apply in-context learning for ABSA by using specific instructions and a few selected examples as prompts. Though promising, LLMs often yield labels that deviate from task requirements. To overcome these limitations, we propose DS2-ABSA, a dual-stream data synthesis framework targeted for few-shot ABSA. It leverages LLMs to synthesize data from two complementary perspectives: textitkey-point-driven and textitinstance-driven, which effectively generate diverse and high-quality ABSA samples in low-resource settings. Furthermore, a textitlabel refinement module is integrated to improve the synthetic labels. Extensive experiments demonstrate that DS2-ABSA significantly outperforms previous few-shot ABSA solutions and other LLM-oriented data generation methods.