MSME: A Multi-Stage Multi-Expert Framework for Zero-Shot Stance Detection
This work addresses stance detection for applications like social media analysis, but it is incremental as it builds on existing LLM-based approaches with modular enhancements.
The paper tackles the challenge of zero-shot stance detection in complex real-world scenarios by proposing MSME, a multi-stage multi-expert framework that integrates knowledge retrieval, specialized reasoning modules, and decision aggregation, achieving state-of-the-art performance on three public datasets.
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.