EmoDynamiX: Emotional Support Dialogue Strategy Prediction by Modelling MiXed Emotions and Discourse Dynamics
This work addresses the need for transparent and unbiased emotional support in conversational AI, offering a domain-specific solution for improving dialogue systems in mental health and counseling applications.
The paper tackles the problem of implicit strategy planning in emotional support dialogue systems by proposing EmoDynamiX, a framework that decouples strategy prediction from language generation, resulting in outperforming previous state-of-the-art methods with significant improvements in proficiency and lower preference bias on two ESC datasets.
Designing emotionally intelligent conversational systems to provide comfort and advice to people experiencing distress is a compelling area of research. Recently, with advancements in large language models (LLMs), end-to-end dialogue agents without explicit strategy prediction steps have become prevalent. However, implicit strategy planning lacks transparency, and recent studies show that LLMs' inherent preference bias towards certain socio-emotional strategies hinders the delivery of high-quality emotional support. To address this challenge, we propose decoupling strategy prediction from language generation, and introduce a novel dialogue strategy prediction framework, EmoDynamiX, which models the discourse dynamics between user fine-grained emotions and system strategies using a heterogeneous graph for better performance and transparency. Experimental results on two ESC datasets show EmoDynamiX outperforms previous state-of-the-art methods with a significant margin (better proficiency and lower preference bias). Our approach also exhibits better transparency by allowing backtracing of decision making.