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 DS$^2$-ABSA, a dual-stream data synthesis framework targeted for few-shot ABSA. It leverages LLMs to synthesize data from two complementary perspectives: \textit{key-point-driven} and \textit{instance-driven}, which effectively generate diverse and high-quality ABSA samples in low-resource settings. Furthermore, a \textit{label refinement} module is integrated to improve the synthetic labels. Extensive experiments demonstrate that DS$^2$-ABSA significantly outperforms previous few-shot ABSA solutions and other LLM-oriented data generation methods.

翻译：近期发展的大型语言模型为应对低资源场景下的数据稀缺问题提供了新的可行途径。在少样本方面级情感分析中，先前的研究已探索了数据增强技术，通过提示大型语言模型修改现有样本来生成新样本。然而，这些方法未能产生足够多样化的数据，从而削弱了其有效性。此外，一些研究通过使用特定指令和少量精选示例作为提示，将上下文学习应用于方面级情感分析。尽管前景可观，但大型语言模型生成的标签常偏离任务要求。为克服这些局限，本文提出DS$^2$-ABSA——一个面向少样本方面级情感分析的双流数据合成框架。该框架利用大型语言模型从两个互补视角合成数据：\textit{关键点驱动}与\textit{实例驱动}，从而在低资源环境下有效生成多样化且高质量的方面级情感分析样本。此外，框架集成了\textit{标签精炼}模块以提升合成标签的质量。大量实验表明，DS$^2$-ABSA显著优于先前的少样本方面级情感分析解决方案及其他基于大型语言模型的数据生成方法。