The Adapter-Bot: All-In-One Controllable Conversational Model

TL;DR

The Adapter-Bot introduces a modular conversational model that integrates multiple dialogue skills and knowledge sources via independently trainable adapters, enabling flexible, controlled, and continual skill addition without retraining the entire system.

Contribution

It presents a novel framework using adapters with a fixed backbone to incorporate diverse dialogue skills and knowledge sources, enhancing control and extensibility in conversational models.

Findings

Achieved automatic evaluation showing improved response quality

Implemented 12 response styles and 8 goal-oriented skills

Released an interactive system for real-world testing

Abstract

Considerable progress has been made towards conversational models that generate coherent and fluent responses by training large language models on large dialogue datasets. These models have little or no control of the generated responses and miss two important features: continuous dialogue skills integration and seamlessly leveraging diverse knowledge sources. In this paper, we propose the Adapter-Bot, a dialogue model that uses a fixed backbone conversational model such as DialGPT (Zhang et al., 2019) and triggers on-demand dialogue skills (e.g., emphatic response, weather information, movie recommendation) via different adapters (Houlsby et al., 2019). Each adapter can be trained independently, thus allowing a continual integration of skills without retraining the entire model. Depending on the skills, the model is able to process multiple knowledge types, such as text, tables, and graphs, in a seamless manner. The dialogue skills can be triggered automatically via a dialogue manager, or manually, thus allowing high-level control of the generated responses. At the current stage, we have implemented 12 response styles (e.g., positive, negative etc.), 8 goal-oriented skills (e.g. weather information, movie recommendation, etc.), and personalized and emphatic responses. We evaluate our model using automatic evaluation by comparing it with existing state-of-the-art conversational models, and we have released an interactive system at adapter.bot.ust.hk.