Zero-Shot Stance Detection using Contextual Data Generation with LLMs
This work addresses data scarcity in stance detection for applications like fake news detection, but it is incremental as it builds on existing methods with limited success.
The authors tackled the problem of scarce labeled data for stance detection by proposing DyMoAdapt, which uses GPT-3 to generate topic-specific data for fine-tuning models at test time, but results did not show expected performance increases, and they introduced the MGT-VAST dataset with multiple topics per context.
Stance detection, the classification of attitudes expressed in a text towards a specific topic, is vital for applications like fake news detection and opinion mining. However, the scarcity of labeled data remains a challenge for this task. To address this problem, we propose Dynamic Model Adaptation with Contextual Data Generation (DyMoAdapt) that combines Few-Shot Learning and Large Language Models. In this approach, we aim to fine-tune an existing model at test time. We achieve this by generating new topic-specific data using GPT-3. This method could enhance performance by allowing the adaptation of the model to new topics. However, the results did not increase as we expected. Furthermore, we introduce the Multi Generated Topic VAST (MGT-VAST) dataset, which extends VAST using GPT-3. In this dataset, each context is associated with multiple topics, allowing the model to understand the relationship between contexts and various potential topics