Chitchat as Interference: Adding User Backstories to Task-Oriented Dialogues
This addresses the issue of natural user interferences in task-oriented dialogue systems, which is incremental as it builds on existing datasets and methods.
The paper tackled the problem of chitchat interference in task-oriented dialogues by enhancing the MultiWOZ dataset with user backstories using few-shot prompting with Llama-2-70B, and found that this addition challenges existing systems but can be used to train models to handle such interference effectively, as confirmed by human evaluation.
During task-oriented dialogues (TODs), human users naturally introduce chitchat that is beyond the immediate scope of the task, interfering with the flow of the conversation. To address this issue without the need for expensive manual data creation, we use few-shot prompting with Llama-2-70B to enhance the MultiWOZ dataset with user backstories, a typical example of chitchat interference in TODs. We assess the impact of this addition by testing two models: one trained solely on TODs and another trained on TODs with a preliminary chitchat interaction. Our analysis demonstrates that our enhanced dataset poses a challenge for these systems. Moreover, we demonstrate that our dataset can be effectively used for training purposes, enabling a system to consistently acknowledge the user's backstory while also successfully moving the task forward in the same turn, as confirmed by human evaluation. These findings highlight the benefits of generating novel chitchat-TOD scenarios to test TOD systems more thoroughly and improve their resilience to natural user interferences