Contextual Dynamic Prompting for Response Generation in Task-oriented Dialog Systems

TL;DR

This paper introduces a contextual dynamic prompting method for response generation in task-oriented dialog systems, leveraging dialog context to improve performance without extensive fine-tuning of large language models.

Contribution

It proposes a novel dynamic prompting approach that learns prompts from dialog context, enhancing response quality in task-oriented systems.

Findings

Improved combined score by 3 points with prompts.

Achieved 20-point boost when dialog states are included.

Human evaluation favored context-aware agents.

Abstract

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 Sch\"utze, 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.