Abstract, Align, Predict: Zero-Shot Stance Detection via Cognitive Inductive Reasoning
This addresses the problem of stance detection for unseen targets in NLP, offering a novel method that reduces reliance on labeled data, though it is incremental in advancing zero-shot techniques.
The paper tackles zero-shot stance detection by proposing the Cognitive Inductive Reasoning Framework (CIRF), which abstracts reasoning schemas from unlabeled text and integrates them via a Schema-Enhanced Graph Kernel Model, achieving new state-of-the-art results with improvements of 1.0, 4.5, and 3.3 percentage points in macro-F1 on three benchmarks and comparable accuracy with 70% fewer labeled examples.
Zero-shot stance detection (ZSSD) aims to identify the stance of text toward previously unseen targets, a setting where conventional supervised models often fail due to reliance on labeled data and shallow lexical cues. Inspired by human cognitive reasoning, we propose the Cognitive Inductive Reasoning Framework (CIRF), which abstracts transferable reasoning schemas from unlabeled text and encodes them as concept-level logic. To integrate these schemas with input arguments, we introduce a Schema-Enhanced Graph Kernel Model (SEGKM) that dynamically aligns local and global reasoning structures. Experiments on SemEval-2016, VAST, and COVID-19-Stance benchmarks show that CIRF establishes new state-of-the-art results, outperforming strong ZSSD baselines by 1.0, 4.5, and 3.3 percentage points in macro-F1, respectively, and achieving comparable accuracy with 70\% fewer labeled examples. We will release the full code upon publication.