A Logically Consistent Chain-of-Thought Approach for Stance Detection

TL;DR

This paper introduces LC-CoT, a novel method for zero-shot stance detection that ensures logical consistency and relevant knowledge extraction, outperforming traditional supervised approaches without requiring labeled data.

Contribution

The paper proposes a three-step LC-CoT approach that improves zero-shot stance detection by maintaining logical coherence and relevance through structured knowledge retrieval and inference.

Findings

Outperforms traditional supervised methods in zero-shot stance detection

Ensures logical consistency in stance predictions

Effectively incorporates external knowledge without labeled data

Abstract

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.