SocialSim: Towards Socialized Simulation of Emotional Support Conversation
This work addresses the high cost of crowdsourcing emotional support conversation data for AI systems, making emotional care more accessible, though it is incremental by building on existing LLM-based augmentation methods.
The paper tackles the problem of simulating emotional support conversations by introducing SocialSim, a framework that integrates social disclosure and awareness, resulting in a synthetic corpus (SSConv) that surpasses crowdsourced data in quality and a chatbot achieving state-of-the-art performance in evaluations.
Emotional support conversation (ESC) helps reduce people's psychological stress and provide emotional value through interactive dialogues. Due to the high cost of crowdsourcing a large ESC corpus, recent attempts use large language models for dialogue augmentation. However, existing approaches largely overlook the social dynamics inherent in ESC, leading to less effective simulations. In this paper, we introduce SocialSim, a novel framework that simulates ESC by integrating key aspects of social interactions: social disclosure and social awareness. On the seeker side, we facilitate social disclosure by constructing a comprehensive persona bank that captures diverse and authentic help-seeking scenarios. On the supporter side, we enhance social awareness by eliciting cognitive reasoning to generate logical and supportive responses. Building upon SocialSim, we construct SSConv, a large-scale synthetic ESC corpus of which quality can even surpass crowdsourced ESC data. We further train a chatbot on SSConv and demonstrate its state-of-the-art performance in both automatic and human evaluations. We believe SocialSim offers a scalable way to synthesize ESC, making emotional care more accessible and practical.