Chatgpt For Zero-shot Dialogue State Tracking: A Solution Or An Opportunity?

Heck Michael, Lubis Nurul, Ruppik Benjamin, Vukovic Renato, Feng Shutong, Geishauser Christian, Lin Hsien-chin, Van Niekerk Carel, Gašić Milica. Arxiv 2023

[Paper]    
Fine Tuning GPT In Context Learning Model Architecture Pretraining Methods Prompting Reinforcement Learning Tools Training Techniques

Recent research on dialogue state tracking (DST) focuses on methods that allow few- and zero-shot transfer to new domains or schemas. However, performance gains heavily depend on aggressive data augmentation and fine-tuning of ever larger language model based architectures. In contrast, general purpose language models, trained on large amounts of diverse data, hold the promise of solving any kind of task without task-specific training. We present preliminary experimental results on the ChatGPT research preview, showing that ChatGPT achieves state-of-the-art performance in zero-shot DST. Despite our findings, we argue that properties inherent to general purpose models limit their ability to replace specialized systems. We further theorize that the in-context learning capabilities of such models will likely become powerful tools to support the development of dedicated and dynamic dialogue state trackers.

Similar Work