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

arXiv: https://arxiv.org/abs/2602.20648 · HTML: https://mlsanity.com/paper/2602.20648/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 9 of its 43 references that are in the map.
- First posted on arXiv 24 Feb 2026.

## Builds on (most cited first, 9 of 9)

- [CoAnnotating: Uncertainty-Guided Work Allocation between Human and Large Language Models for Data Annotation](https://mlsanity.com/paper/2310.15638/) (2023)
- [A Computational Framework for Behavioral Assessment of LLM Therapists](https://mlsanity.com/paper/2401.00820/) (2024)
- [Evaluation of ChatGPT for NLP-based Mental Health Applications](https://mlsanity.com/paper/2303.15727/) (2023)
- [Towards a Client-Centered Assessment of LLM Therapists by Client Simulation](https://mlsanity.com/paper/2406.12266/) (2024)
- [Rethinking Large Language Models in Mental Health Applications](https://mlsanity.com/paper/2311.11267/) (2023)
- [Deep Annotation of Therapeutic Working Alliance in Psychotherapy](https://mlsanity.com/paper/2204.05522/) (2022)
- [Exploring the Efficacy of Large Language Models in Summarizing Mental Health Counseling Sessions: A Benchmark Study](https://mlsanity.com/paper/2402.19052/) (2024)
- [Working Alliance Transformer for Psychotherapy Dialogue Classification](https://mlsanity.com/paper/2210.15603/) (2022)
- [COMPASS: Computational Mapping of Patient-Therapist Alliance Strategies with Language Modeling](https://mlsanity.com/paper/2402.14701/) (2024)

## Abstract (arXiv)

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.