Zero-shot stance detection (ZSSD) aims to detect stances toward unseen targets. Incorporating background knowledge to enhance transferability between seen and unseen targets constitutes the primary approach of ZSSD. However, these methods often struggle with a knowledge-task disconnect and lack logical consistency in their predictions. To address these issues, we introduce a novel approach named Logically Consistent Chain-of-Thought (LC-CoT) for ZSSD, which improves stance detection by ensuring relevant and logically sound knowledge extraction. LC-CoT employs a three-step process. Initially, it assesses whether supplementary external knowledge is necessary. Subsequently, it uses API calls to retrieve this knowledge, which can be processed by a separate LLM. Finally, a manual exemplar guides the LLM to infer stance categories, using an if-then logical structure to maintain relevance and logical coherence. This structured approach to eliciting background knowledge enhances the model's capability, outperforming traditional supervised methods without relying on labeled data.

翻译：零样本立场检测（ZSSD）旨在检测针对未见目标的立场。引入背景知识以增强已见与未见目标之间的可迁移性构成了ZSSD的主要方法。然而，这些方法常面临知识与任务脱节的问题，且预测结果缺乏逻辑一致性。为解决这些问题，我们针对ZSSD提出了一种名为逻辑一致思维链（LC-CoT）的新方法，通过确保知识提取的相关性与逻辑严谨性来改进立场检测。LC-CoT采用三步流程：首先评估是否需要补充外部知识，随后通过API调用获取可由独立LLM处理的知识，最后借助人工范例引导LLM基于"if-then"逻辑结构推断立场类别，以维持相关性与逻辑连贯性。这种结构化背景知识获取方法增强了模型能力，在无需依赖标注数据的情况下超越了传统监督方法。