arXiv 2606.265712026-06-26cs.CL

零样本推文级立场检测：外部知识与反思性思维链推理增强

Zero-shot Tweet-Level Stance Detection Enhanced by External Knowledge and Reflective Chain-of-Thought Reasoning

School of Cyber Science and Engineering, Sichuan University（四川大学网络空间安全学院）；School of Cyberspace Science and Technology, Beijing Jiaotong University（北京交通大学网络空间安全学院）

Yiju Huang, Wenxian Wang, Lijun Zhou, Rui Tang, Xiao Lan, Tao Zhang, Haizhou Wang

阅读 PDF

arXiv 页面 ↗HTML 原文 ↗

AI总结：

针对零样本推文级立场检测中文本稀疏和目标-文本关联难题，提出KIRP框架，融合外部知识、实体重组、反思性思维链推理和立场感知对比学习，在三个数据集上取得最优性能。

摘要：

零样本推文级立场检测面临两个主要挑战：(1) 缓解短文本固有的上下文稀疏性，(2) 建立隐式目标与文本内容之间的相关性。现有方法主要关注引入外部知识，却忽略了关键文本内实体中蕴含的内在语义线索。此外，当前模型在确定未见目标与给定文本的相关性方面能力有限，因此难以区分“中立”和“无关”立场标签。为解决这些问题，我们首先构建了一个四类、多主题的日语推文数据集。据我们所知，这是首个用于立场检测的日语推文级数据集。然后，我们提出了KIRP，一个零样本立场检测框架。它整合了外部知识与实体重组以进行数据增强，并采用提示链进行推理。具体而言，该框架引入知识图谱来补充和重组关键文本实体，同时反思性思维链推理提取并验证隐式目标。为了更好地区分“中立”和“无关”标签，我们采用立场感知对比学习来捕获判别性特征，并设计了一个三层迭代原型网络用于细粒度分类。在SemEval-2016、WT-WT和KIRP-D上的实验结果表明，KIRP达到了最先进的性能。KIRP在SemEval-2016上获得84.05%（三分类）的F1分数，在WT-WT和KIRP-D上分别获得84.99%和79.18%（四分类）的F1分数。

英文摘要：

Zero-shot tweet-level stance detection confronts two primary challenges: (1) mitigating the context sparsity inherent in short texts, and (2) establishing the relevance between implicit targets and textual content. While existing methods primarily focus on incorporating external knowledge, they neglect the intrinsic semantic cues embedded within key intra-textual entities. Furthermore, current models exhibit limited capability in determining the relevance of unseen targets to the given text, thereby struggling to differentiate between "neutral" and "irrelevant" stance labels. To address these issues, we first construct a four-class, multi-topic Japanese tweet dataset. To our knowledge, this is the first Japanese tweet-level dataset for stance detection. We then propose KIRP, a zero-shot stance detection framework. It integrates external knowledge with entity reorganization for data augmentation and employs prompt chaining for reasoning. Specifically, the framework incorporates knowledge graphs to supplement and reorganize key textual entities, while reflective Chain-of-Thought (CoT) reasoning extracts and validates implicit targets. To better distinguish "neutral" from "irrelevant" labels, we adopt stance-aware contrastive learning to capture discriminative features and design a three-layer iterative prototype network for fine-grained classification. Experimental results on SemEval-2016, WT-WT, and KIRP-D show that KIRP achieves state-of-the-art performance. KIRP obtains F1 scores of 84.05% (three-class) on SemEval-2016, and 84.99% and 79.18% (four-class) on WT-WT and KIRP-D, respectively.

机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。