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

arXiv: https://arxiv.org/abs/2412.14849 · HTML: https://mlsanity.com/paper/2412.14849/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Placed in Self-training for few-shot NLP, one of 13 directions in Synthetic data and self-improvement for LLMs.
- Builds on 6 of its 51 references that are in the map.
- First posted on arXiv 19 Dec 2024.

## Placed in

- Synthetic data and self-improvement for LLMs / [Self-training for few-shot NLP](https://mlsanity.com/synth/self-training-for-few-shot-nlp/)

## Builds on (most cited first, 6 of 6)

- [GPT-4 Technical Report](https://mlsanity.com/paper/2303.08774/) (2023)
- [The Llama 3 Herd of Models](https://mlsanity.com/paper/2407.21783/) (2024)
- [Scaling Synthetic Data Creation with 1,000,000,000 Personas](https://mlsanity.com/paper/2406.20094/) (2024)
- [AugGPT: Leveraging ChatGPT for Text Data Augmentation](https://mlsanity.com/paper/2302.13007/) (2023)
- [Key-Point-Driven Data Synthesis with its Enhancement on Mathematical Reasoning](https://mlsanity.com/paper/2403.02333/) (2024)
- [Large language models for aspect-based sentiment analysis](https://mlsanity.com/paper/2310.18025/) (2023)

## Built on by (most cited first, 2 of 2)

- [When LLMs Team Up: The Emergence of Collaborative Affective Computing](https://mlsanity.com/paper/2506.01698/) (2025)
- [Semantic-preserved Augmentation with Confidence-weighted Fine-tuning for Aspect Category Sentiment Analysis](https://mlsanity.com/paper/2506.07148/) (2025)

## Abstract (arXiv)

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.