Challenge: Existing models for stance detection are not robust enough to be used in a viewpoint-diverse news recommender because the news constantly has new discussion topics.
Approach: They propose to use two stance task definitions (Pro/Con versus Same Side Stance) and two LLM architectures (bi-encoding versus cross-encode) to test model performance.
Outcome: The proposed models outperform the same side-stance definition and other models on stance across different topics.

Similar Papers

LLM-Driven Knowledge Injection Advances Zero-Shot and Cross-Target Stance Detection (2024.naacl-short)

Copied to clipboard

Challenge: Existing methods for stance detection focus on background information and not on the accompanying input texts.
Approach: They propose to prompt Large Language Models to explicitly extract the relationship between paired text and unseen target as contextual knowledge and inject it into a generation model BART to exploit the rich contexts and semantics.
Outcome: The proposed model is able to detect stance labels in zero-shot and cross-target scenarios.
Zero-Shot Stance Detection: A Dataset and Model using Generalized Topic Representations (2020.emnlp-main)

Copied to clipboard

Challenge: Existing methods for stance detection are topic-specific and cross-target stance.
Approach: They propose a new dataset for zero-shot stance detection that captures a wider range of topics and lexical variation than in previous datasets.
Outcome: The proposed model improves performance on a number of challenging linguistic phenomena.
Are Stereotypes Leading LLMs’ Zero-Shot Stance Detection ? (2025.emnlp-main)

Copied to clipboard

Challenge: Large Language Models inherit stereotypes from their pretraining data, leading to biased behavior toward certain social groups in many tasks.
Approach: They propose to annotate posts in pre-existing stance detection datasets with dialect or vernacular of a specific group and text complexity/readability to investigate whether these attributes influence the model’s stance detect decisions.
Outcome: The proposed model exhibits significant stereotypes when performing stance detection tasks in a zero-shot setting.
Target Really Matters: Target-aware Contrastive Learning and Consistency Regularization for Few-shot Stance Detection (2022.coling-1)

Copied to clipboard

Challenge: stance detection is a task to identify attitudes from opinions towards certain targets, but it is expensive and time-consuming . stance detector is based on labeled data, but unlabeled data can be collected easier .
Approach: They propose a semi-supervised framework for few-shot stance detection that uses unlabeled data to learn more distinguishable representations for different targets.
Outcome: The proposed framework achieves state-of-the-art performance on multiple benchmark datasets.
Zero-Shot and Few-Shot Stance Detection on Varied Topics via Conditional Generation (2023.acl-short)

Copied to clipboard

Challenge: Existing work on stance detection focuses on in-domain or leave-out targets with only a few target choices.
Approach: They propose to use a conditional generation framework to denoise from partially-filled templates to better utilize the semantics among input, label, and target texts.
Outcome: The proposed method significantly outperforms strong baselines on VAST and achieves new state-of-the-art performance.
Contrastive Language Adaptation for Cross-Lingual Stance Detection (D19-1)

Copied to clipboard

Challenge: Current approaches to fact-checking are time-consuming and tedious.
Approach: They propose a novel approach which leverages labeled data in one language to identify relative perspective of a document with respect to a claim in a different target language.
Outcome: The proposed approach can deal with the challenge of limited labeled data in the target language.
Modeling Human-Like Cognition for Stance Detection: Integrating Intuitive Judgment and Analytical Reasoning (2026.acl-long)

Copied to clipboard

Challenge: Recent advances in large language models (LLMs) have revolutionized stance detection, enabling complex reasoning strategies such as chain-of-thought prompting.
Approach: They propose Cognitive-Driven Stance Detection (CDSD) that integrates fast intuitive judgment and analytical reasoning enhanced by three key modules: attention-based cognitive alignment to compare system focus, uncertainty-aware belief update using Bayesian inference, and self-doubt-triggered counterfactual reasoning for re-evaluation under low consistency or high uncertainty.
Outcome: The proposed method outperforms state-of-the-art methods on SEM16, P-Stance, and VAST.
TATA: Stance Detection via Topic-Agnostic and Topic-Aware Embeddings (2023.emnlp-main)

Copied to clipboard

Challenge: Recent studies have focused on topic-specific stance classifiers that fail to generalize to unseen topics.
Approach: They propose to use contrastive learning and an unlabeled dataset to train topic-agnostic/TAG and topic-aligned/TAW embeddings for use in downstream stance detection.
Outcome: The proposed model achieves state-of-the-art performance across several public stance detection datasets (0.771 F1-score on the Zero-shot VAST dataset).
Stance Reasoner: Zero-Shot Stance Detection on Social Media with Explicit Reasoning (2024.lrec-main)

Copied to clipboard

Challenge: Stance Reasoner is a model for zero-shot stance detection on social media platforms that can be used to extract opinions from opinionated content.
Approach: They propose a method that leverages explicit reasoning over background knowledge to guide the model’s inference about the document’s stance on a target.
Outcome: The proposed model outperforms the current state-of-the-art models on 3 Twitter datasets, including fully supervised models.
A Challenge Dataset and Effective Models for Conversational Stance Detection (2024.lrec-main)

Copied to clipboard

Challenge: stance detection studies focus on evaluating stances within individual instances, hindering progress of conversational stance analysis.
Approach: They propose a multi-turn conversation stance detection dataset that encompasses multiple targets for conversational stance detector.
Outcome: The proposed dataset encompasses multiple targets for conversational stance detection.

What is GenGO?

GenGO is an NLP powered publication search system. It currenctly indexes 30k+ papers from ACL Anthology, and implements multi-aspect summarization, semantic search, and more!

Information

About
Limitations