Commonsense-Aware Prompting for Controllable Empathetic Dialogue Generation (2302.01441v1)

Abstract: Improving the emotional awareness of pre-trained LLMs is an emerging important problem for dialogue generation tasks. Although prior studies have introduced methods to improve empathetic dialogue generation, few have discussed how to incorporate commonsense knowledge into pre-trained LLMs for controllable dialogue generation. In this study, we propose a novel framework that improves empathetic dialogue generation using pre-trained LLMs by 1) incorporating commonsense knowledge through prompt verbalization, and 2) controlling dialogue generation using a strategy-driven future discriminator. We conducted experiments to reveal that both the incorporation of social commonsense knowledge and enforcement of control over generation help to improve generation performance. Finally, we discuss the implications of our study for future research.