# S2IT: Stepwise Syntax Integration Tuning for Large Language Models in Aspect Sentiment Quad Prediction

arXiv: https://arxiv.org/abs/2604.23296 · HTML: https://mlsanity.com/paper/2604.23296/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 8 of its 17 references that are in the map.
- First posted on arXiv 25 Apr 2026.

## Builds on (most cited first, 8 of 8)

- [Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer](https://mlsanity.com/paper/1910.10683/) (2019)
- [LoRA: Low-Rank Adaptation of Large Language Models](https://mlsanity.com/paper/2106.09685/) (2021)
- [Aspect Sentiment Quad Prediction as Paraphrase Generation](https://mlsanity.com/paper/2110.00796/) (2021)
- [A Unified Generative Framework for Aspect-Based Sentiment Analysis](https://mlsanity.com/paper/2106.04300/) (2021)
- [Graphix-T5: Mixing Pre-Trained Transformers with Graph-Aware Layers for Text-to-SQL Parsing](https://mlsanity.com/paper/2301.07507/) (2023)
- [MvP: Multi-view Prompting Improves Aspect Sentiment Tuple Prediction](https://mlsanity.com/paper/2305.12627/) (2023)
- [Improving Aspect Sentiment Quad Prediction via Template-Order Data Augmentation](https://mlsanity.com/paper/2210.10291/) (2022)
- [BiSyn-GAT+: Bi-Syntax Aware Graph Attention Network for Aspect-based Sentiment Analysis](https://mlsanity.com/paper/2204.03117/) (2022)

## Abstract (arXiv)

Aspect Sentiment Quad Prediction (ASQP) has seen significant advancements, largely driven by the powerful semantic understanding and generative capabilities of large language models (LLMs). However, while syntactic structure information has been proven effective in previous extractive paradigms, it remains underutilized in the generative paradigm of LLMs due to their limited reasoning capabilities. In this paper, we propose S^2IT, a novel Stepwise Syntax Integration Tuning framework that progressively integrates syntactic structure knowledge into LLMs through a multi-step tuning process. The training process is divided into three steps. S^2IT decomposes the quadruple generation task into two stages: 1) Global Syntax-guided Extraction and 2) Local Syntax-guided Classification, integrating both global and local syntactic structure information. Finally, Fine-grained Structural Tuning enhances the model's understanding of syntactic structures through the prediction of element links and node classification. Experiments demonstrate that S^2IT significantly improves state-of-the-art performance across multiple datasets. Our implementation will be open-sourced at https://github.com/DMIRLAB-Group/S2IT.