Dynamic Label Name Refinement for Few-Shot Dialogue Intent Classification
This addresses challenges in dialogue systems for users by improving intent classification accuracy in few-shot scenarios, though it is incremental as it builds on existing in-context learning methods.
The paper tackles the problem of few-shot dialogue intent classification by proposing a dynamic label refinement approach using in-context learning with large language models, which resolves confusion between semantically similar intents and significantly enhances performance across multiple datasets.
Dialogue intent classification aims to identify the underlying purpose or intent of a user's input in a conversation. Current intent classification systems encounter considerable challenges, primarily due to the vast number of possible intents and the significant semantic overlap among similar intent classes. In this paper, we propose a novel approach to few-shot dialogue intent classification through in-context learning, incorporating dynamic label refinement to address these challenges. Our method retrieves relevant examples for a test input from the training set and leverages a large language model to dynamically refine intent labels based on semantic understanding, ensuring that intents are clearly distinguishable from one another. Experimental results demonstrate that our approach effectively resolves confusion between semantically similar intents, resulting in significantly enhanced performance across multiple datasets compared to baselines. We also show that our method generates more interpretable intent labels, and has a better semantic coherence in capturing underlying user intents compared to baselines.