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.
@article{arxiv.2604.01671,
title = {PRCCF: A Persona-guided Retrieval and Causal-aware Cognitive Filtering Framework for Emotional Support Conversation},
author = {Yanxin Luo and Xiaoyu Zhang and Jing Li and Yan Gao and Donghong Han},
journal= {arXiv preprint arXiv:2604.01671},
year = {2026}
}
Comments
14 pages, 6 figures, 5 tables. Submitted to Transactions of the Association for Computational Linguistics (TACL)