Can You Put it All Together: Evaluating Conversational Agents' Ability to Blend Skills
Eric Michael Smith, Mary Williamson, Kurt Shuster, Jason Weston, Y-Lan Boureau
TL;DR
The paper tackles the challenge of blending open-domain dialogue skills by evaluating several training schemes to combine single-skill models and by introducing the BlendedSkillTalk dataset. It demonstrates that multi-task training yields superior blended performance and that bias mitigation and fine-tuning on blended data further enhance results. Through automated metrics and human evaluations, the study shows balanced, credible performance across knowledge, empathy, and personal topics, with two-stage and multi-task approaches offering complementary advantages. The work provides a practical pathway toward open-domain agents capable of seamlessly integrating multiple skills and sets the stage for incorporating additional capabilities in future research.
Abstract
Being engaging, knowledgeable, and empathetic are all desirable general qualities in a conversational agent. Previous work has introduced tasks and datasets that aim to help agents to learn those qualities in isolation and gauge how well they can express them. But rather than being specialized in one single quality, a good open-domain conversational agent should be able to seamlessly blend them all into one cohesive conversational flow. In this work, we investigate several ways to combine models trained towards isolated capabilities, ranging from simple model aggregation schemes that require minimal additional training, to various forms of multi-task training that encompass several skills at all training stages. We further propose a new dataset, BlendedSkillTalk, to analyze how these capabilities would mesh together in a natural conversation, and compare the performance of different architectures and training schemes. Our experiments show that multi-tasking over several tasks that focus on particular capabilities results in better blended conversation performance compared to models trained on a single skill, and that both unified or two-stage approaches perform well if they are constructed to avoid unwanted bias in skill selection or are fine-tuned on our new task.