Stance Detection on Social Media with Fine-Tuned Large Language Models
This work addresses stance detection for social media analysis, but it is incremental as it applies existing fine-tuning methods to new models without introducing novel techniques.
This study tackled stance detection on social media by fine-tuning large language models like ChatGPT, LLaMa-2, and Mistral-7B, finding that all models surpassed existing benchmarks with LLaMa-2 and Mistral-7B showing remarkable efficiency despite their smaller sizes.
Stance detection, a key task in natural language processing, determines an author's viewpoint based on textual analysis. This study evaluates the evolution of stance detection methods, transitioning from early machine learning approaches to the groundbreaking BERT model, and eventually to modern Large Language Models (LLMs) such as ChatGPT, LLaMa-2, and Mistral-7B. While ChatGPT's closed-source nature and associated costs present challenges, the open-source models like LLaMa-2 and Mistral-7B offers an encouraging alternative. Initially, our research focused on fine-tuning ChatGPT, LLaMa-2, and Mistral-7B using several publicly available datasets. Subsequently, to provide a comprehensive comparison, we assess the performance of these models in zero-shot and few-shot learning scenarios. The results underscore the exceptional ability of LLMs in accurately detecting stance, with all tested models surpassing existing benchmarks. Notably, LLaMa-2 and Mistral-7B demonstrate remarkable efficiency and potential for stance detection, despite their smaller sizes compared to ChatGPT. This study emphasizes the potential of LLMs in stance detection and calls for more extensive research in this field.