# OpenStance: Real-world Zero-shot Stance Detection

arXiv: https://arxiv.org/abs/2210.14299 · HTML: https://mlsanity.com/paper/2210.14299/

## Key facts

- Cited by 7 papers in the map (data through 14 Oct 2026).
- Builds on 21 of its 37 references that are in the map.
- First posted on arXiv 25 Oct 2022.

## Builds on (most cited first, 21 of 21)

- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [Language Models are Few-Shot Learners](https://mlsanity.com/paper/2005.14165/) (2020)
- [RoBERTa: A Robustly Optimized BERT Pretraining Approach](https://mlsanity.com/paper/1907.11692/) (2019)
- [Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks](https://mlsanity.com/paper/1908.10084/) (2019)
- [A Broad-Coverage Challenge Corpus for Sentence Understanding through Inference](https://mlsanity.com/paper/1704.05426/) (2017)
- [ConceptNet 5.5: An Open Multilingual Graph of General Knowledge](https://mlsanity.com/paper/1612.03975/) (2016)
- [Want To Reduce Labeling Cost? GPT-3 Can Help](https://mlsanity.com/paper/2108.13487/) (2021)
- [GPT3Mix: Leveraging Large-scale Language Models for Text Augmentation](https://mlsanity.com/paper/2104.08826/) (2021)
- [Zero-Shot Stance Detection: A Dataset and Model using Generalized Topic Representations](https://mlsanity.com/paper/2010.03640/) (2020)
- [Seeing Things from a Different Angle: Discovering Diverse Perspectives about Claims](https://mlsanity.com/paper/1906.03538/) (2019)
- [Label Verbalization and Entailment for Effective Zero- and Few-Shot Relation Extraction](https://mlsanity.com/paper/2109.03659/) (2021)
- [Will-They-Won't-They: A Very Large Dataset for Stance Detection on Twitter](https://mlsanity.com/paper/2005.00388/) (2020)
- [Universal Natural Language Processing with Limited Annotations: Try Few-shot Textual Entailment as a Start](https://mlsanity.com/paper/2010.02584/) (2020)
- [Adversarial Learning for Zero-Shot Stance Detection on Social Media](https://mlsanity.com/paper/2105.06603/) (2021)
- [Incremental Few-shot Text Classification with Multi-round New Classes: Formulation, Dataset and System](https://mlsanity.com/paper/2104.11882/) (2021)
- [Textual Entailment for Event Argument Extraction: Zero- and Few-Shot with Multi-Source Learning](https://mlsanity.com/paper/2205.01376/) (2022)
- [Ultra-fine Entity Typing with Indirect Supervision from Natural Language Inference](https://mlsanity.com/paper/2202.06167/) (2022)
- [Nowcasting the Stance of Social Media Users in a Sudden Vote: The Case of the Greek Referendum](https://mlsanity.com/paper/1808.08538/) (2018)
- [Stance Prediction for Russian: Data and Analysis](https://mlsanity.com/paper/1809.01574/) (2018)
- [Stance detection in online discussions](https://mlsanity.com/paper/1701.00504/) (2017)
- [Stance Detection in Turkish Tweets](https://mlsanity.com/paper/1706.06894/) (2017)

## Built on by (most cited first, 7 of 7)

- [Large Language Model Instruction Following: A Survey of Progresses and Challenges](https://mlsanity.com/paper/2303.10475/) (2023)
- [Can Large Language Models Address Open-Target Stance Detection?](https://mlsanity.com/paper/2409.00222/) (2024)
- [Stanceformer: Target-Aware Transformer for Stance Detection](https://mlsanity.com/paper/2410.07083/) (2024)
- [EDDA: A Encoder-Decoder Data Augmentation Framework for Zero-Shot Stance Detection](https://mlsanity.com/paper/2403.15715/) (2024)
- [Data-Centric AI in the Age of Large Language Models](https://mlsanity.com/paper/2406.14473/) (2024)
- [X-Shot: A Unified System to Handle Frequent, Few-shot and Zero-shot Learning Simultaneously in Classification](https://mlsanity.com/paper/2403.03863/) (2024)
- [Zero-Shot Stance Detection in the Wild: Dynamic Target Generation and Multi-Target Adaptation](https://mlsanity.com/paper/2601.19802/) (2026)

## Abstract (arXiv)

Prior studies of zero-shot stance detection identify the attitude of texts towards unseen topics occurring in the same document corpus. Such task formulation has three limitations: (i) Single domain/dataset. A system is optimized on a particular dataset from a single domain; therefore, the resulting system cannot work well on other datasets; (ii) the model is evaluated on a limited number of unseen topics; (iii) it is assumed that part of the topics has rich annotations, which might be impossible in real-world applications. These drawbacks will lead to an impractical stance detection system that fails to generalize to open domains and open-form topics. This work defines OpenStance: open-domain zero-shot stance detection, aiming to handle stance detection in an open world with neither domain constraints nor topic-specific annotations. The key challenge of OpenStance lies in the open-domain generalization: learning a system with fully unspecific supervision but capable of generalizing to any dataset. To solve OpenStance, we propose to combine indirect supervision, from textual entailment datasets, and weak supervision, from data generated automatically by pre-trained Language Models. Our single system, without any topic-specific supervision, outperforms the supervised method on three popular datasets. To our knowledge, this is the first work that studies stance detection under the open-domain zero-shot setting. All data and code are publicly released.