Empathetic Dialogue
Empathetic dialogue research aims to create conversational agents capable of understanding and responding to users' emotions, fostering more human-like and supportive interactions. Current research focuses on developing models that leverage large language models (LLMs) and incorporate various techniques, such as emotion recognition, commonsense knowledge integration, and multi-modal data (including acoustic and physiological signals), to generate empathetic responses. This field is significant for advancing human-computer interaction, with potential applications in mental health support, education, and customer service, driving improvements in both the design and evaluation of conversational AI systems.
Papers
Human-AI Collaboration Enables More Empathic Conversations in Text-based Peer-to-Peer Mental Health Support
Ashish Sharma, Inna W. Lin, Adam S. Miner, David C. Atkins, Tim Althoff
STUDIES: Corpus of Japanese Empathetic Dialogue Speech Towards Friendly Voice Agent
Yuki Saito, Yuto Nishimura, Shinnosuke Takamichi, Kentaro Tachibana, Hiroshi Saruwatari