MSME: A Multi-Stage Multi-Expert Framework for Zero-Shot Stance Detection

TL;DR

This paper introduces MSME, a multi-stage, multi-expert framework that enhances zero-shot stance detection by integrating background knowledge, specialized reasoning modules, and pragmatic analysis, achieving state-of-the-art results.

Contribution

The paper presents a novel multi-stage, multi-expert approach that explicitly models background knowledge, reasoning, and pragmatic cues for improved zero-shot stance detection.

Findings

MSME outperforms existing methods on three public datasets.

The framework effectively handles complex real-world stance detection scenarios.

Expert modules contribute significantly to overall performance.

Abstract

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.