Search papers, labs, and topics across Lattice.
Graph2Counsel generates synthetic counseling dialogues by prompting LLMs with Client Psychological Graphs (CPGs), encoding relationships between a client's thoughts, emotions, and behaviors, and counselor strategies. The framework explores prompting strategies like Chain-of-Thought and Multi-Agent Feedback to improve the psychological consistency and realism of the generated dialogues. Expert evaluations show that Graph2Counsel outperforms existing datasets in specificity, counselor competence, authenticity, conversational flow, and safety, and fine-tuning on the generated data improves performance on downstream counseling benchmarks.
Synthetic counseling dialogues can be made significantly more realistic and useful for fine-tuning by grounding them in structured Client Psychological Graphs that capture the interplay of a client's thoughts, emotions, and behaviors.
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.
