Cognitive Policy-Driven LLM for Diagnosis and Intervention of Cognitive Distortions in Emotional Support Conversation

TL;DR

This paper introduces CoPoLLM, a novel LLM framework for diagnosing and intervening in cognitive distortions during emotional support conversations, supported by a new dataset and theoretical safety analysis.

Contribution

It presents the first dataset with cognitive distortion labels and a new LLM framework that improves diagnosis, intervention, and safety in emotional support tasks.

Findings

CoPoLLM outperforms 15 baselines in diagnosis accuracy.

CoPoLLM enhances intervention strategy effectiveness.

CoPoLLM offers safety risk control advantages.

Abstract

Emotional Support Conversation (ESC) plays a critical role in mental health assistance by providing accessible psychological support in real-world applications. Large Language Models (LLMs) have shown strong empathetic abilities in ESC tasks. Yet, existing methods overlook the issue of cognitive distortions in help-seekers' expressions. As a result, current models can only provide basic emotional comfort, rather than helping help-seekers address their psychological distress at a deeper cognitive level. To address this challenge, we construct the CogBiasESC dataset, the first dataset that expands existing ESC datasets by adding labels for cognitive distortions, includes their type, intensity, and safe risk level. Furthermore, we propose the Cognitive Policy-driven Large Language Model framework (CoPoLLM) to enhance LLMs' ability to diagnose and intervene cognitive distortions in help-seekers. We also analyze the safety advantages of CoPoLLM from a theoretical perspective. Experimental results show that CoPoLLM significantly outperforms 15 state-of-the-art baselines in terms of distortion diagnosis accuracy, intervention strategy effectiveness, and safety risk control.