无需预设目标，自动识别社交媒体中的多立场关系。
Zero-Shot Stance Detection in the Wild: Dynamic Target Generation and Multi-Target Adaptation
- 动态生成目标并适配多目标，实现零样本立场检测。
- 两阶段微调的Qwen2.5-7B目标识别准确率达66.99%。
- 适合研究真实场景下立场分析与大模型应用的读者。
当前立场检测研究通常基于给定目标和文本进行判断，但在真实社交媒体场景中，目标既非预定义也非静态，而是复杂且动态的。为应对这一挑战，我们提出新任务：在无监督环境下通过动态目标生成与多目标适应（DGTA）实现零样本立场检测，旨在从文本中自动识别多个目标-立场对，无需事先知晓目标。我们构建了中文社交媒体立场检测数据集，并设计多维度评估指标。探索了大语言模型（LLMs）的联合微调与两阶段微调策略，评估多种基线模型。实验结果表明，微调后的大型语言模型表现优异：两阶段微调的Qwen2.5-7B在目标识别上取得最高综合得分66.99%，而联合微调的DeepSeek-R1-Distill-Qwen-7B在立场检测上达到79.26%的F1分数。
原文摘要 · Abstract (English)
Current stance detection research typically relies on predicting stance based on given targets and text. However, in real-world social media scenarios, targets are neither predefined nor static but rather complex and dynamic. To address this challenge, we propose a novel task: zero-shot stance detection in the wild with Dynamic Target Generation and Multi-Target Adaptation (DGTA), which aims to automatically identify multiple target-stance pairs from text without prior target knowledge. We construct a Chinese social media stance detection dataset and design multi-dimensional evaluation metrics. We explore both integrated and two-stage fine-tuning strategies for large language models (LLMs) and evaluate various baseline models. Experimental results demonstrate that fine-tuned LLMs achieve superior performance on this task: the two-stage fine-tuned Qwen2.5-7B attains the highest comprehensive target recognition score of 66.99%, while the integrated fine-tuned DeepSeek-R1-Distill-Qwen-7B achieves a stance detection F1 score of 79.26%.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。