PRCCF: A Persona-guided Retrieval and Causal-aware Cognitive Filtering Framework for Emotional Support Conversation
This work addresses emotional distress alleviation in conversational AI, representing an incremental improvement in domain-specific methods.
The paper tackles the challenge of deep contextual understanding in Emotional Support Conversation by proposing PRCCF, a framework that integrates persona-guided retrieval and causality-aware cognitive filtering, which outperforms state-of-the-art baselines on the ESConv dataset in both automatic metrics and human evaluations.
Emotional Support Conversation (ESC) aims to alleviate individual emotional distress by generating empathetic responses. However, existing methods face challenges in effectively supporting deep contextual understanding. To address this issue, we propose PRCCF, a Persona-guided Retrieval and Causality-aware Cognitive Filtering framework. Specifically, the framework incorporates a persona-guided retrieval mechanism that jointly models semantic compatibility and persona alignment to enhance response generation. Furthermore, it employs a causality-aware cognitive filtering module to prioritize causally relevant external knowledge, thereby improving contextual cognitive understanding for emotional reasoning. Extensive experiments on the ESConv dataset demonstrate that PRCCF outperforms state-of-the-art baselines on both automatic metrics and human evaluations. Our code is publicly available at: https://github.com/YancyLyx/PRCCF.