EMNLP Findings2024
Stanceformer: Target-Aware Transformer for Stance Detection
Abstract
The task of Stance Detection involves discerning the stance expressed in a text towards a specific subject or target. Prior works have relied on existing transformer models that lack the capability to prioritize targets effectively. Consequently, these models yield similar performance regardless of whether we utilize or disregard target information, undermining the task's significance. To address this challenge, we introduce Stanceformer, a target-aware transformer model that incorporates enhanced attention towards the targets during both training and inference. Specifically, we design a Target Awareness matrix that increases the selfattention scores assigned to the targets. We demonstrate the efficacy of the Stanceformer with various BERT-based models, including state-of-the-art models and Large Language Models (LLMs), and evaluate its performance across three stance detection datasets, alongside a zero-shot dataset. Our approach Stanceformer not only provides superior performance but also generalizes even to other domains, such as Aspect-based Sentiment Analysis. We make the code publicly available. 1
Ask Lune
Know this paper in minutes, not an afternoon.
Lune can read every page of it and the top-tier papers that cite it, and gives you its claims, its evidence and its limits, each one cited to the paper it comes from. No skimming, no AI slop.
2 top-tier papers have cited it since. Know what they found before your reviewers do.
Lune can draw on
the full paper · the top-tier papers that cite it · related work
Free to start. No credit card required.
Lineage
- Finetuned Language Models are Zero-Shot Learners cites Language Models are Few-Shot Learners
- MPRF: Interpretable Stance Detection through Multi-Path Reasoning Framework cites Enhancing Zero-shot and Few-shot Stance Detection with Commonsense Knowledge Graph
- MPRF: Interpretable Stance Detection through Multi-Path Reasoning Framework cites P-Stance: A Large Dataset for Stance Detection in Political Domain
- MPRF: Interpretable Stance Detection through Multi-Path Reasoning Framework cites Language Models are Few-Shot Learners
- MPRF: Interpretable Stance Detection through Multi-Path Reasoning Framework cites JointCL: A Joint Contrastive Learning Framework for Zero-Shot Stance Detection
- JointCL: A Joint Contrastive Learning Framework for Zero-Shot Stance Detection cites Enhancing Zero-shot and Few-shot Stance Detection with Commonsense Knowledge Graph
Cited by top-tier papers2
Builds on16
- Language Models are Few-Shot LearnersTom B. Brown, Benjamin Mann, Nick Ryder, Melanie Subbiah et al.NeurIPS 2020 · 64,255 citations
- Finetuned Language Models are Zero-Shot LearnersJason Wei, Maarten Bosma, Vincent Y. Zhao, Kelvin Guu et al.ICLR 2022 · 4,966 citations
- JointCL: A Joint Contrastive Learning Framework for Zero-Shot Stance DetectionBin Liang, Qinglin Zhu, Xiang Li, Min Yang et al.ACL 2022 · 117 citations
- P-Stance: A Large Dataset for Stance Detection in Political DomainYingjie Li, Tiberiu Sosea, Aditya Sawant, Ajith Jayaraman Nair et al.ACL Findings 2021 · 98 citations
- Enhancing Zero-shot and Few-shot Stance Detection with Commonsense Knowledge GraphRui Liu, Zheng Lin, Yutong Tan, Weiping WangACL Findings 2021 · 97 citations
Related papers
- A New Direction in Stance Detection: Target-Stance Extraction in the WildYingjie Li, Krishna Garg, Cornelia CarageaACL 2023 · 7 citations
- Few-Shot Stance Detection via Target-Aware Prompt DistillationYan Jiang, Jinhua Gao, Huawei Shen, Xueqi ChengSIGIR 2022 · 29 citations
- Improving Multi-task Stance Detection with Multi-task Interaction NetworkHeyan Chai, Siyu Tang, Jinhao Cui, Ye Ding et al.EMNLP 2022 · 7 citations
- Can Large Language Models Address Open-Target Stance Detection?Abu Ubaida Akash, Ahmed Fahmy, Amine TrabelsiACL Findings 2025 · 3 citations
- LLM-Driven Implicit Target Augmentation and Fine-Grained Contextual Modeling for Zero-Shot and Few-Shot Stance DetectionYanxu Ji, Jinzhong Ning, Yi-Jia Zhang, Zhi Liu et al.EMNLP 2025
