AI Paper Atlas

Research map / Large language models / Agents, code and math

CARE-Bench: A Benchmark of Diverse Client Simulations Guided by Expert Principles for Evaluating LLMs in Psychological Counseling

Bichen Wang, Yixin Sun, Junzhe Wang, Hao Yang, Xing Fu, Yanyan Zhao, Si Wei, Shijin Wang, Bing Qin

AAAI 2026 · Large language models › Agents, code and math · approach: Mathematical and structural reasoning benchmarks

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
add expert-guided principles to the profile-based client simulation (ablation)LLM client simulator (Qwen2.5-Max) · Human evaluation: Authenticity7-point Likert score: +0.40 ***Improved
add expert-guided principles to the profile-based client simulation (ablation)LLM client simulator (Qwen2.5-Max) · Human evaluation: Stayed in Role7-point Likert score: +0.23 **Improved
add expert-guided principles to the profile-based client simulation (ablation)LLM client simulator (Qwen2.5-Max) · Human evaluation: Resembled Typical Case7-point Likert score: +0.36 ***Improved
add expert-guided principles to the profile-based client simulation (ablation)LLM client simulator (Qwen2.5-Max) · Human evaluation: Challenged the Counselor7-point Likert score: +0.25 **Improved
add expert-guided principles to the profile-based client simulation (ablation)LLM client simulator (Qwen2.5-Max) · Human evaluation: Ready as Training Partner7-point Likert score: +0.23 **Improved
add expert-guided principles to the profile-based client simulation (ablation)LLM client simulator (Qwen2.5-Max) · Human evaluation: Recommend to Novices7-point Likert score: +0.31 ***Improved
use a reasoning model as counselor (Deepseek-R1 vs GPT-4o)counselor LLM · CARE-Bench (CCS-R)CCS-R avg: 3.81 -> 4.39Improved
scale Llama-3.1 from 8B to 70Bcounselor LLM · CARE-Bench (WAI)WAI avg: 3.51 -> 3.59Improved
use counseling-specialized model (CPsyCounX) vs GPT-4ocounselor LLM · CARE-Bench (BLRI)BLRI avg: 1.59 -> 1.68Improved
client has low openness, conscientiousness, agreeableness or high neuroticismcounselor LLMs · CARE-Benchcounseling scoreHurt

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy