# Induce, Align, Predict: Zero-Shot Stance Detection via Cognitive Inductive Reasoning

arXiv: https://arxiv.org/abs/2506.13470 · HTML: https://mlsanity.com/paper/2506.13470/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Placed in Causal reasoning in LLMs, one of 17 directions in LLM reasoning.
- Builds on 4 of its 47 references that are in the map.
- First posted on arXiv 16 Jun 2025.

## Placed in

- LLM reasoning / [Causal reasoning in LLMs](https://mlsanity.com/lr/causal-reasoning-in-llms/)

## Builds on (most cited first, 4 of 4)

- [Investigating Chain-of-thought with ChatGPT for Stance Detection on Social Media](https://mlsanity.com/paper/2304.03087/) (2023)
- [Harvesting Event Schemas from Large Language Models](https://mlsanity.com/paper/2305.07280/) (2023)
- [Generative Induction of Dialogue Task Schemas with Streaming Refinement and Simulated Interactions](https://mlsanity.com/paper/2504.18474/) (2025)
- [Few-Shot Learning of Visual Compositional Concepts through Probabilistic Schema Induction](https://mlsanity.com/paper/2505.09859/) (2025)

## Built on by (most cited first, 1 of 1)

- [When Annotators Agree but Labels Disagree: The Projection Problem in Stance Detection](https://mlsanity.com/paper/2603.24231/) (2026)

## Abstract (arXiv)

Zero-shot stance detection (ZSSD) seeks to determine the stance of text toward previously unseen targets, a task critical for analyzing dynamic and polarized online discourse with limited labeled data. While large language models (LLMs) offer zero-shot capabilities, prompting-based approaches often fall short in handling complex reasoning and lack robust generalization to novel targets. Meanwhile, LLM-enhanced methods still require substantial labeled data and struggle to move beyond instance-level patterns, limiting their interpretability and adaptability. Inspired by cognitive science, we propose the Cognitive Inductive Reasoning Framework (CIRF), a schema-driven method that bridges linguistic inputs and abstract reasoning via automatic induction and application of cognitive reasoning schemas. CIRF abstracts first-order logic patterns from raw text into multi-relational schema graphs in an unsupervised manner, and leverages a schema-enhanced graph kernel model to align input structures with schema templates for robust, interpretable zero-shot inference. Extensive experiments on SemEval-2016, VAST, and COVID-19-Stance benchmarks demonstrate that CIRF not only establishes new state-of-the-art results, but also achieves comparable performance with just 30% of the labeled data, demonstrating its strong generalization and efficiency in low-resource settings.