DS2-ABSA: Dual-Stream Data Synthesis with Label Refinement for Few-Shot Aspect-Based Sentiment Analysis
Year: 2025
Type: conference-paper
Abstract: 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.Additionally, some studies apply incontext 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: key-point-driven and instancedriven, which effectively generate diverse and high-quality ABSA samples in low-resource settings.Furthermore, a label refinement module is integrated to improve the synthetic labels.Extensive experiments demonstrate that DS 2 -ABSA significantly outperforms previous fewshot ABSA solutions and other LLM-oriented data generation methods.
Authors: Hongling Xu, Yice Zhang, Qianlong Wang, Ruifeng Xu
Institution: Harbin Institute of Technology
Language: English
Subfield: Artificial Intelligence
Field: Computer Science
Domain: Physical Sciences
Open Access status: hybrid
Awards: G2230680632, G6312846351, G7349572720
OpenAlex ID: W4412945248