Contextual Dynamic Prompting for Response Generation in Task-oriented Dialog Systems
This work addresses the problem of resource-intensive fine-tuning for large language models in dialog systems, offering a more efficient alternative, though it is incremental as it builds on existing prompting methods.
The paper tackles response generation in task-oriented dialog systems by proposing contextual dynamic prompting, which learns prompts from dialog contexts, and shows improvements of 3 absolute points in combined score and 20 points when incorporating dialog states on the MultiWOZ 2.2 dataset.
Response generation is one of the critical components in task-oriented dialog systems. Existing studies have shown that large pre-trained language models can be adapted to this task. The typical paradigm of adapting such extremely large language models would be by fine-tuning on the downstream tasks which is not only time-consuming but also involves significant resources and access to fine-tuning data. Prompting (Schick and Schütze, 2020) has been an alternative to fine-tuning in many NLP tasks. In our work, we explore the idea of using prompting for response generation in task-oriented dialog systems. Specifically, we propose an approach that performs contextual dynamic prompting where the prompts are learnt from dialog contexts. We aim to distill useful prompting signals from the dialog context. On experiments with MultiWOZ 2.2 dataset (Zang et al., 2020), we show that contextual dynamic prompts improve response generation in terms of combined score (Mehri et al., 2019) by 3 absolute points, and a massive 20 points when dialog states are incorporated. Furthermore, human annotation on these conversations found that agents which incorporate context were preferred over agents with vanilla prefix-tuning.