Research

Paper

AI LLM February 24, 2026

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

Authors

Anqi Li, Chenxiao Wang, Yu Lu, Renjun Xu, Lizhi Ma, Zhenzhong Lan

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.

Metadata

arXiv ID: 2602.20648
Provider: ARXIV
Primary Category: cs.CL
Published: 2026-02-24
Fetched: 2026-02-25 06:05

Related papers

Raw Data (Debug)
{
  "raw_xml": "<entry>\n    <id>http://arxiv.org/abs/2602.20648v1</id>\n    <title>CARE: An Explainable Computational Framework for Assessing Client-Perceived Therapeutic Alliance Using Large Language Models</title>\n    <updated>2026-02-24T07:52:56Z</updated>\n    <link href='https://arxiv.org/abs/2602.20648v1' rel='alternate' type='text/html'/>\n    <link href='https://arxiv.org/pdf/2602.20648v1' rel='related' title='pdf' type='application/pdf'/>\n    <summary>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.</summary>\n    <category scheme='http://arxiv.org/schemas/atom' term='cs.CL'/>\n    <published>2026-02-24T07:52:56Z</published>\n    <arxiv:comment>14 pages, 4 figures</arxiv:comment>\n    <arxiv:primary_category term='cs.CL'/>\n    <author>\n      <name>Anqi Li</name>\n    </author>\n    <author>\n      <name>Chenxiao Wang</name>\n    </author>\n    <author>\n      <name>Yu Lu</name>\n    </author>\n    <author>\n      <name>Renjun Xu</name>\n    </author>\n    <author>\n      <name>Lizhi Ma</name>\n    </author>\n    <author>\n      <name>Zhenzhong Lan</name>\n    </author>\n  </entry>"
}