多专家协作框架提升零样本立场识别准确率
MSME: A Multi-Stage Multi-Expert Framework for Zero-Shot Stance Detection
- 分三阶段：知识准备、专家推理、决策融合
- 在三个数据集上均达到当前最优效果
- 适合处理复杂语境下的讽刺、复合实体等难题
基于大模型的零样本立场检测方法虽已取得显著进展，但在复杂现实场景中仍面临挑战：立场理解需动态背景知识，目标定义涉及复合实体或事件且需明确关联立场标签，修辞手法如反讽常掩盖作者真实意图。为此，本文提出多阶段多专家框架MSME。该框架包含三个阶段：(1) 知识准备，检索相关背景知识并澄清立场标签；(2) 专家推理，包含三个专精模块——知识专家从知识角度提炼关键事实与理由，标签专家相应优化立场标签与解释，语用专家从语用角度检测反讽等修辞线索以推断真实意图；(3) 决策聚合，由元裁判整合所有专家分析结果生成最终立场判断。在三个公开数据集上的实验表明，MSME在各项指标上均达到当前最优表现。
原文摘要 · Abstract (English)
LLM-based approaches have recently achieved impressive results in zero-shot stance detection. However, they still struggle in complex real-world scenarios, where stance understanding requires dynamic background knowledge, target definitions involve compound entities or events that must be explicitly linked to stance labels, and rhetorical devices such as irony often obscure the author's actual intent. To address these challenges, we propose MSME, a Multi-Stage, Multi-Expert framework for zero-shot stance detection. MSME consists of three stages: (1) Knowledge Preparation, where relevant background knowledge is retrieved and stance labels are clarified; (2) Expert Reasoning, involving three specialized modules-Knowledge Expert distills salient facts and reasons from a knowledge perspective, Label Expert refines stance labels and reasons accordingly, and Pragmatic Expert detects rhetorical cues such as irony to infer intent from a pragmatic angle; (3) Decision Aggregation, where a Meta-Judge integrates all expert analyses to produce the final stance prediction. Experiments on three public datasets show that MSME achieves state-of-the-art performance across the board.
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。