Graph2Counsel: Clinically Grounded Synthetic Counseling Dialogue Generation from Client Psychological Graphs

TL;DR

Graph2Counsel is a novel framework that generates realistic synthetic counseling dialogues grounded in client psychological graphs, addressing data scarcity and structural consistency issues in mental health LLM applications.

Contribution

It introduces a structured prompting pipeline guided by client psychological graphs and counselor strategies, producing high-quality synthetic counseling sessions for training and evaluation.

Findings

Generated 760 sessions from 76 CPGs across diverse profiles.

Outperforms prior datasets in authenticity and safety in expert evaluations.

Fine-tuning models on this data improves downstream counseling benchmarks.

Abstract

Rising demand for mental health support has increased interest in using Large Language Models (LLMs) for counseling. However, adapting LLMs to this high-risk safety-critical domain is hindered by the scarcity of real-world counseling data due to privacy constraints. Synthetic datasets provide a promising alternative, but existing approaches often rely on unstructured or semi-structured text inputs and overlook structural dependencies between a client's cognitive, emotional, and behavioral states, often producing psychologically inconsistent interactions and reducing data realism and quality. We introduce Graph2Counsel, a framework for generating synthetic counseling sessions grounded in Client Psychological Graphs (CPGs) that encode relationships among clients' thoughts, emotions, and behaviors. Graph2Counsel employs a structured prompting pipeline guided by counselor strategies and CPG, and explores prompting strategies including CoT (Wei et al., 2022) and Multi-Agent Feedback (Li et al., 2025a). Graph2Counsel produces 760 sessions from 76 CPGs across diverse client profiles. In expert evaluation, our dataset outperforms prior datasets on specificity, counselor competence, authenticity, conversational flow, and safety, with substantial inter-annotator agreement (Krippendorff's $\alpha$ = 0.70). Fine-tuning an open-source model on this dataset improves performance on CounselingBench (Nguyen et al., 2025) and CounselBench (Li et al., 2025b), showing downstream utility. We also make our code and data public.