Large Language Models Meet Stance Detection: A Survey of Tasks, Methods, Applications, Challenges and Future Directions

2025-05-13

AI Summary

Existing research lacks a systematic survey of large language models (LLMs) for stance detection. This paper introduces the first three-dimensional taxonomy—spanning learning paradigms, data modalities, and target relations—specifically designed for LLM-based stance detection. We comprehensively review task formalizations, methodological advances—including supervised, few-shot, and zero-shot learning; multimodal fusion; prompt engineering; and instruction tuning—as well as emerging challenges such as implicit stance modeling and mitigation of cultural bias. We conduct unified benchmarking of mainstream LLMs across 12 standard datasets, empirically assessing their efficacy and limitations in real-world applications like fake news detection and sentiment-aware舆情 analysis. Our findings yield a principled roadmap and practical guidelines for both theoretical advancement and industrial deployment of stance detection systems.

Technology Category

• Machine Learning: Large Multimodal Models (LMMs)
• Natural Language Processing: Fact-Checking / Misinformation Detection (NLP Focus)
• Computer Vision: Large Vision Models

Application Category

• User Modeling, Personalization and Recommendation: Large Language Models (LLM) for user modeling and recommendation
• Semantics and Knowledge: Data modeling to support human-machine intelligence, including LLMs agents, intelligent system behavior, explanations, and user-friendly interactions
• Search and Retrieval-Augmented AI: Large language models for search

Abstract

Stance detection is essential for understanding subjective content across various platforms such as social media, news articles, and online reviews. Recent advances in Large Language Models (LLMs) have revolutionized stance detection by introducing novel capabilities in contextual understanding, cross-domain generalization, and multimodal analysis. Despite these progressions, existing surveys often lack comprehensive coverage of approaches that specifically leverage LLMs for stance detection. To bridge this critical gap, our review article conducts a systematic analysis of stance detection, comprehensively examining recent advancements of LLMs transforming the field, including foundational concepts, methodologies, datasets, applications, and emerging challenges. We present a novel taxonomy for LLM-based stance detection approaches, structured along three key dimensions: 1) learning methods, including supervised, unsupervised, few-shot, and zero-shot; 2) data modalities, such as unimodal, multimodal, and hybrid; and 3) target relationships, encompassing in-target, cross-target, and multi-target scenarios. Furthermore, we discuss the evaluation techniques and analyze benchmark datasets and performance trends, highlighting the strengths and limitations of different architectures. Key applications in misinformation detection, political analysis, public health monitoring, and social media moderation are discussed. Finally, we identify critical challenges such as implicit stance expression, cultural biases, and computational constraints, while outlining promising future directions, including explainable stance reasoning, low-resource adaptation, and real-time deployment frameworks. Our survey highlights emerging trends, open challenges, and future directions to guide researchers and practitioners in developing next-generation stance detection systems powered by large language models.

Problem

• Surveying LLM-based stance detection tasks and methods
• Addressing gaps in existing stance detection surveys
• Exploring challenges like bias and real-time deployment

Innovation

• LLMs enhance contextual understanding in stance detection
• Taxonomy covers learning methods, data modalities, target relationships
• Addresses challenges like implicit stance and cultural biases