Miracle: Towards Personalized Dialogue Generation with Latent-Space Multiple Personal Attribute Control

Abstract

Personalized dialogue systems aim to endow the chatbot agent with more anthropomorphic traits for human-like interactions. Previous approaches have explored explicitly user profile modeling using text descriptions, implicit derivation of user embeddings, or utilizing handicraft prompts for ChatGPT-like models. However, textual personas are limited in describing multi-faceted attributes (e.g., language style, inner character nuances), implicit embedding suffers from personality sparsity, and handicraft prompts lack fine-grained and stable controllability. Hence, these approaches may struggle with complex personalized dialogue generation tasks that require generating controllable responses with multiple personal attributes. To this end, we propose MIRACLE, a novel personalized dialogue generation method through MultIple PeRsonal Attributes Control within Latent-Space Energybased Models. Specifically, our approach first disentangles complex personality into multifaceted attributes. Subsequently, we employ a conditional variational auto-encoder to align with the dense personalized responses within a latent joint attribute space. We have also tailored a dedicated energy function and customized the ordinary differential equations sampling method to offer flexible attribute composition and precise attribute control. Extensive experiments demonstrate that MIRA-CLE outperforms state-of-the-art models regarding both personality controllability and response generation quality. Our dataset and code are available at https://github.com/ LZY-the-boys/MIRACLE

A Missionary Training Program For University Students In South Korea

“…With 1 in every 8 people confirming they have experienced mental disorders (WHO, 2022), estimates suggest that nearly half of the global population will encounter mental health challenges at some point (McGrath et al, 2023). This trend underscores the need for effective and personalized support systems tailored to meet the needs of individuals (Lu et al, 2023;Chen et al, 2023a). Moreover, the rise of digital platforms has transformed communication, increasing the demand for online support and engagement.…”