2023/12/26 by Bowen Zhang, Daijun Ding, Zhang, Bowen +5
Computer Science · Engineering · #Anomaly Detection Techniques and Applications #Computation and Language (cs.CL) #FOS: Computer and information sciences #Geophysical Methods and Applications #Video Surveillance and Tracking Methods
paper · pdf · doi:10.48550/arxiv.2312.16054
openalex publication_date 2023/12/26 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28
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.