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.
Anthology ID:
2023.findings-emnlp.273
Volume:
Findings of the Association for Computational Linguistics: EMNLP 2023
Month:
December
Year:
2023
Address:
Singapore
Editors:
Houda Bouamor, Juan Pino, Kalika Bali
Venue:
Findings
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
4154–4161
Language:
URL:
https://aclanthology.org/2023.findings-emnlp.273
DOI:
10.18653/v1/2023.findings-emnlp.273
Bibkey:
Cite (ACL):
Joseph Gatto, Omar Sharif, and Sarah Preum. 2023. Chain-of-Thought Embeddings for Stance Detection on Social Media. In Findings of the Association for Computational Linguistics: EMNLP 2023, pages 4154–4161, Singapore. Association for Computational Linguistics.
Cite (Informal):
Chain-of-Thought Embeddings for Stance Detection on Social Media (Gatto et al., Findings 2023)
Copy Citation:
PDF:
https://aclanthology.org/2023.findings-emnlp.273.pdf