Lune

EMNLP Findings2023

Chain-of-Thought Embeddings for Stance Detection on Social Media

Joseph Gatto, Omar Sharif, Sarah Preum

Abstract

Stance detection on social media is challenging for Large Language Models (LLMs), as emerging slang and colloquial language in online conversations often contain deeply implicit stance labels. Chain-of-Thought (COT) prompting has recently been shown to improve performance on stance detection tasks -alleviating some of these issues. However, COT prompting still struggles with implicit stance identification. This challenge arises because many samples are initially challenging to comprehend before a model becomes familiar with the slang and evolving knowledge related to different topics, all of which need to be acquired through the training data. In this study, we address this problem by introducing COT Embeddings which improve COT performance on stance detection tasks by embedding COT reasonings and integrating them into a traditional RoBERTa-based stance detection pipeline. Our analysis demonstrates that 1) text encoders can leverage COT reasonings with minor errors or hallucinations that would otherwise distort the COT output label. 2) Text encoders can overlook misleading COT reasoning when a sample's prediction heavily depends on domain-specific patterns. Our model achieves SOTA performance on multiple stance detection datasets collected from social media.

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.

6 top-tier papers have cited it since. Know what they found before your reviewers do.

Questions to start from

Lune can draw on

the full paper · the top-tier papers that cite it · related work

Get the answer

Free to start. No credit card required.

Lineage

  • Exploring Artificial Image Generation for Stance Detection cites TweetEval: Unified Benchmark and Comparative Evaluation for Tweet Classification
  • Journalism-Guided Agentic In-context Learning for News Stance Detection cites Chain-of-Thought Prompting Elicits Reasoning in Large Language Models
  • Bilingual Zero-Shot Stance Detection cites Enhancing Zero-shot and Few-shot Stance Detection with Commonsense Knowledge Graph
  • MPVStance: Mitigating Hallucinations in Stance Detection with Multi-Perspective Verification cites Enhancing Zero-shot and Few-shot Stance Detection with Commonsense Knowledge Graph
  • TwiUSD: A Benchmark Dataset and Structure-Aware LLM Framework for User Stance Detection cites Enhancing Zero-shot and Few-shot Stance Detection with Commonsense Knowledge Graph
Builds onCited byLeft to right by year; the more cited, the higher.

Cited by top-tier papers6

  1. Bilingual Zero-Shot Stance DetectionChenye Zhao, Cornelia CarageaACL 2025 · 1 citation
  2. MPVStance: Mitigating Hallucinations in Stance Detection with Multi-Perspective VerificationZhaodan Zhang, Zhao Zhang, Jin Zhang, Hui Xu et al.ACL 2025 · 1 citation
  3. Exploring Artificial Image Generation for Stance DetectionZhengkang Zhang, Zhongqing Wang, Guodong ZhouEMNLP 2025
  4. Journalism-Guided Agentic In-context Learning for News Stance DetectionDahyun Lee, Jonghyeon Choi, Jiyoung Han, Kunwoo ParkEMNLP 2025
  5. TwiUSD: A Benchmark Dataset and Structure-Aware LLM Framework for User Stance DetectionFuqiang Niu, Zini Chen, Zhiyu Xie, Hu Huang et al.ACL 2026

Builds on6

  1. Chain-of-Thought Prompting Elicits Reasoning in Large Language ModelsJason Wei, Xuezhi Wang, Dale Schuurmans, Maarten Bosma et al.NeurIPS 2022 · 22,562 citations
  2. TweetEval: Unified Benchmark and Comparative Evaluation for Tweet ClassificationFrancesco Barbieri, José Camacho-Collados, Luis Espinosa Anke, Leonardo NevesEMNLP Findings 2020 · 720 citations
  3. SKEP: Sentiment Knowledge Enhanced Pre-training for Sentiment AnalysisHao Tian, Can Gao, Xinyan Xiao, Hao Liu et al.ACL 2020 · 265 citations
  4. BertGCN: Transductive Text Classification by Combining GNN and BERTYuxiao Lin, Yuxian Meng, Xiaofei Sun, Qinghong Han et al.ACL Findings 2021 · 229 citations
  5. 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

  1. Chain-of-Thought Prompting Obscures Hallucination Cues in Large Language Models: An Empirical EvaluationJiahao Cheng, Tiancheng Su, Jia Yuan, Guoxiu He et al.EMNLP Findings 2025 · 11 citations
  2. Tree-of-Counterfactual Prompting for Zero-Shot Stance DetectionMaxwell A. Weinzierl, Sanda M. HarabagiuACL 2024
  3. LaRS: Latent Reasoning Skills for Chain-of-Thought ReasoningZifan Xu, Haozhu Wang, Dmitriy Bespalov, Xian Wu et al.EMNLP Findings 2024 · 4 citations
  4. A Reinforcement Learning Framework for Cross-Lingual Stance Detection Using Chain-of-Thought AlignmentBinghui Li, Minghui Zou, Xiaowang Zhang, Shizhan Chen et al.ACL Findings 2025 · 2 citations
  5. SemCoT: Accelerating Chain-of-Thought Reasoning through Semantically-Aligned Implicit TokensYinhan He, Wendy Zheng, Yaochen Zhu, Zaiyi Zheng et al.NeurIPS 2025 · 19 citations
Dusk over the sea between two cliffs drawn in fine vertical lines