通过分步整合语法结构，提升大模型在情感四元组预测中的表现
$\mathcal{S}^2$IT: Stepwise Syntax Integration Tuning for Large Language Models in Aspect Sentiment Quad Prediction
- 分三步逐步将语法信息注入大模型，先全局提取再局部分类
- 在多个数据集上显著超越现有方法，提升明显且稳定
- 适合需要精准句法理解的文本分析任务研究者使用
情感四元组预测（ASQP）近年来取得显著进展，主要得益于大语言模型（LLMs）强大的语义理解与生成能力。然而，尽管语法结构在以往抽取式方法中已被证明有效，但在大模型的生成式范式中仍因推理能力有限而未被充分利用。本文提出S^2IT——一种分步语法融合调优框架，通过多阶段调优过程逐步将语法结构知识融入大模型。训练分为三个步骤：首先进行全局语法引导的抽取，其次执行局部语法引导的分类，最后通过细粒度结构调优，增强模型对元素间连接和节点分类的理解。实验表明，S^2IT在多个数据集上显著提升当前最优性能。代码将开源于https://github.com/DMIRLAB-Group/S2IT。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。