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

arXiv: https://arxiv.org/abs/2512.04492 · HTML: https://mlsanity.com/paper/2512.04492/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- Builds on 18 of its 45 references that are in the map.
- First posted on arXiv 4 Dec 2025.

## Builds on (most cited first, 18 of 18)

- [Llama 2: Open Foundation and Fine-Tuned Chat Models](https://mlsanity.com/paper/2307.09288/) (2023)
- [AgentVerse: Facilitating Multi-Agent Collaboration and Exploring Emergent Behaviors](https://mlsanity.com/paper/2308.10848/) (2023)
- [ProcessBench: Identifying Process Errors in Mathematical Reasoning](https://mlsanity.com/paper/2412.06559/) (2024)
- [A Comprehensive Capability Analysis of GPT-3 and GPT-3.5 Series Models](https://mlsanity.com/paper/2303.10420/) (2023)
- [OpenPrompt: An Open-source Framework for Prompt-learning](https://mlsanity.com/paper/2111.01998/) (2021)
- [BERT: A Review of Applications in Natural Language Processing and Understanding](https://mlsanity.com/paper/2103.11943/) (2021)
- [Zero-Shot Stance Detection: A Dataset and Model using Generalized Topic Representations](https://mlsanity.com/paper/2010.03640/) (2020)
- [Aspect-based Sentiment Classification with Aspect-specific Graph Convolutional Networks](https://mlsanity.com/paper/1909.03477/) (2019)
- [Will-They-Won't-They: A Very Large Dataset for Stance Detection on Twitter](https://mlsanity.com/paper/2005.00388/) (2020)
- [Stance Detection with Collaborative Role-Infused LLM-Based Agents](https://mlsanity.com/paper/2310.10467/) (2023)
- [Cross-Target Stance Classification with Self-Attention Networks](https://mlsanity.com/paper/1805.06593/) (2018)
- [Adversarial Learning for Zero-Shot Stance Detection on Social Media](https://mlsanity.com/paper/2105.06603/) (2021)
- [Cross-Domain Label-Adaptive Stance Detection](https://mlsanity.com/paper/2104.07467/) (2021)
- [A Context-Aware Citation Recommendation Model with BERT and Graph Convolutional Networks](https://mlsanity.com/paper/1903.06464/) (2019)
- [Stance Reasoner: Zero-Shot Stance Detection on Social Media with Explicit Reasoning](https://mlsanity.com/paper/2403.14895/) (2024)
- [Topical Stance Detection for Twitter: A Two-Phase LSTM Model Using Attention](https://mlsanity.com/paper/1801.03032/) (2018)
- [STEM: Unsupervised STructural EMbedding for Stance Detection](https://mlsanity.com/paper/2112.00712/) (2021)
- [Stance Prediction for Contemporary Issues: Data and Experiments](https://mlsanity.com/paper/2006.00052/) (2020)

## Built on by (most cited first, 3 of 3)

- [Zero-Shot Stance Detection in the Wild: Dynamic Target Generation and Multi-Target Adaptation](https://mlsanity.com/paper/2601.19802/) (2026)
- [When Annotators Agree but Labels Disagree: The Projection Problem in Stance Detection](https://mlsanity.com/paper/2603.24231/) (2026)
- [Towards High-Level Semantic Intelligence](https://mlsanity.com/paper/2607.24082/) (2026)

## Abstract (arXiv)

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.