CARE: An Explainable Computational Framework for Assessing Client-Perceived Therapeutic Alliance Using Large Language Models

TL;DR

CARE is an LLM-based framework that predicts client-perceived therapeutic alliance scores from counseling transcripts, providing interpretable rationales and outperforming existing methods in accuracy and contextual understanding.

Contribution

The paper introduces CARE, a novel LLM-based system that automatically assesses therapeutic alliance with interpretable rationales, improving accuracy and contextual modeling over prior approaches.

Findings

CARE achieves over 70% higher correlation with client ratings.

Rationale-augmented supervision enhances predictive accuracy.

The framework uncovers common alliance challenges in real-world sessions.

Abstract

Client perceptions of the therapeutic alliance are critical for counseling effectiveness. Accurately capturing these perceptions remains challenging, as traditional post-session questionnaires are burdensome and often delayed, while existing computational approaches produce coarse scores, lack interpretable rationales, and fail to model holistic session context. We present CARE, an LLM-based framework to automatically predict multi-dimensional alliance scores and generate interpretable rationales from counseling transcripts. Built on the CounselingWAI dataset and enriched with 9,516 expert-curated rationales, CARE is fine-tuned using rationale-augmented supervision with the LLaMA-3.1-8B-Instruct backbone. Experiments show that CARE outperforms leading LLMs and substantially reduces the gap between counselor evaluations and client-perceived alliance, achieving over 70% higher Pearson correlation with client ratings. Rationale-augmented supervision further improves predictive accuracy. CARE also produces high-quality, contextually grounded rationales, validated by both automatic and human evaluations. Applied to real-world Chinese online counseling sessions, CARE uncovers common alliance-building challenges, illustrates how interaction patterns shape alliance development, and provides actionable insights, demonstrating its potential as an AI-assisted tool for supporting mental health care.