analiza aiqbench
Graph2Counsel addresses the critical data scarcity in mental health AI by leveraging Client Psychological Graphs to generate structurally consistent synthetic counseling sessions. This approach overcomes the limitations of unstructured text inputs, resulting in datasets that demonstrate superior safety, authenticity, and counselor competence when used to fine-tune open-source models. The release of this framework and its associated evaluation tools offers a robust pathway for developing reliable LLM applications in safety-critical therapeutic environments.
Graph2Counsel: Clinically Grounded Synthetic Counseling Dialogue Generation from Client Psychological Graphs
arXiv:2604.20382v2 Announce Type: replace Abstract: Rising demand for mental health support has increased interest in using Large Language Models (LLMs) for counseling, but adapting them to this safety-critical domain is hindered by limited real-world 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, leading to psychologically inconsistent and less realistic interactions. 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 uses a structured prompting pipeline guided by counselor strategies and CPG, and explores prompting strategies including CoT and Multi-Agent Feedback. It 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 (Krippendorff's $\alpha$ = 0.70). Fine-tuning an open-source model on this dataset improves performance on several metrics on CounselingBench and CounselBench, while matching baselines on others. We further introduce Therapy-Eval, a multi-turn evaluation framework, and demonstrate the effectiveness of our fine-tuned model in realistic therapeutic conversations. We make our code, data and fine-tuned model public.
Abstract:Rising demand for mental health support has increased interest in using Large Language Models (LLMs) for counseling, but adapting them to this safety-critical domain is hindered by limited real-world 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, leading to psychologically inconsistent and less realistic interactions. 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 uses a structured prompting pipeline guided by counselor strategies and CPG, and explores prompting strategies including CoT and Multi-Agent Feedback. It 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 (Krippendorff's $\alpha$ = 0.70). Fine-tuning an open-source model on this dataset improves performance on several metrics on CounselingBench and CounselBench, while matching baselines on others. We further introduce Therapy-Eval, a multi-turn evaluation framework, and demonstrate the effectiveness of our fine-tuned model in realistic therapeutic conversations. We make our code, data and fine-tuned model public.
Computation and Language (cs.CL)
arXiv:2604.20382 [cs.CL]
(or arXiv:2604.20382v2 [cs.CL] for this version)
https://doi.org/10.48550/arXiv.2604.20382 Focus to learn more arXiv-issued DOI via DataCite
arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.
Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.
Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.
Text integral sub licența deschisă a publicației · 292 cuvinte
Subiecte conexe
DeepSAGE: Stage-Aware Reinforcement Learning for Structured CBT Counseling Dialogue
arXiv · 25 aug. 2026
Multi-Objective Aligned Small Language Model Framework for SUD Patient Dialogue Generation
arXiv · 8 oct. 2026
DMT-CBT: Longitudinal Therapeutic State Modeling for CBT Counseling
arXiv · 3 iun. 2026
ODRA: Synthesizing Cognitive Behavioral Therapy Sessions with Structured Chain-Of-Thought and Dynamic Patient Resistance
arXiv · 6 aug. 2026