arXiv 2604.016712026-04-02cs.CL

PRCCF: 一种基于人格的检索与因果感知认知过滤框架用于情感支持对话

PRCCF: A Persona-guided Retrieval and Causal-aware Cognitive Filtering Framework for Emotional Support Conversation

School of Computer Science and Engineering, Northeastern University, Shenyang, Liaoning, China（东北大学计算机科学与工程学院，沈阳，辽宁，中国）；Oracle Cloud Infrastructure, Oracle, Santa Clara, CA, United States（甲骨文云基础设施，甲骨文公司，圣克拉拉，加利福尼亚州，美国）

Yanxin Luo, Xiaoyu Zhang, Jing Li, Yan Gao, Donghong Han

备注：: 14 pages, 6 figures, 5 tables. Submitted to Transactions of the Association for Computational Linguistics (TACL)

阅读 PDF

arXiv 页面 ↗HTML 原文 ↗

AI总结：

PRCCF通过结合语义兼容性和人格对齐的检索机制，以及因果感知的认知过滤模块，提升情感支持对话中上下文认知理解能力，在ESConv数据集上优于现有方法。

摘要：

情感支持对话（ESC）旨在通过生成共情回应缓解个体情绪困扰。然而，现有方法在有效支持深度上下文理解方面面临挑战。为此，我们提出PRCCF，一种基于人格的检索与因果感知认知过滤框架。具体而言，该框架包含一个基于人格的检索机制，联合建模语义兼容性和人格对齐以增强回应生成。此外，它采用因果感知的认知过滤模块，优先考虑因果相关的外部知识，从而提升情感推理的上下文认知理解。在ESConv数据集上的大量实验表明，PRCCF在自动指标和人工评估上均优于现有最先进基线。我们的代码已公开在：https://github.com/YancyLyx/PRCCF。

英文摘要：

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.

机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。