Graph2Counsel: Clinically Grounded Synthetic Counseling Dialogue Generation from Client Psychological Graphs
This addresses the scarcity of real counseling data for adapting LLMs in a high-risk domain, though it is incremental as it builds on existing prompting methods.
The paper tackles the problem of generating synthetic counseling dialogues for mental health applications by introducing Graph2Counsel, a framework that uses Client Psychological Graphs to produce 760 sessions, which expert evaluation shows outperform prior datasets on metrics like specificity and safety with Krippendorff's α = 0.70, and fine-tuning on this data improves performance on benchmarks.
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 $α$ = 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.