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

• URL: http://arxiv.org/abs/2604.20382v1
• Date: Wed, 22 Apr 2026 09:31:56 GMT
• Title: Graph2Counsel: Clinically Grounded Synthetic Counseling Dialogue Generation from Client Psychological Graphs
• Abstract summary: Graph2Counsel is a framework for generating synthetic counseling sessions grounded in Client Psychological Graphs.<n>Our dataset outperforms prior datasets on specificity, counselor competence, authenticity, conversational flow, and safety.
• Score: 45.85014131829635
• License: http://creativecommons.org/licenses/by/4.0/
• 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 $α$ = 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.

Related papers

• PatientAct: Theory-Grounded Mental Health Client Simulation [41.20618039157054]
  We present PatientAct, a framework for client simulation grounded in established clinical theories.<n>Our profiles integrate the 5Ps clinical case formulation, providing causal depth without tying the design to any single therapeutic modality.<n>PatientAct significantly outperforms the baselines, yielding substantial gains in resistance quality and behavioral realism.
  arXiv  Detail & Related papers  (2026-08-13T03:01:15Z)
• PsyCLIENT: Client Simulation via Conversational Trajectory Modeling for Trainee Practice and Model Evaluation in Mental Health Counseling [26.381095576860925]
  PsyCLIENT is a novel simulation framework grounded in conversational trajectory modeling.<n>We introduce PsyCLIENT-CP, the first open-source Chinese client profile dataset.<n>Code and data will be released to facilitate future research in mental health counseling.
  arXiv  Detail & Related papers  (2026-01-12T08:33:05Z)
• Towards Federated Clustering: A Client-wise Private Graph Aggregation Framework [57.04850867402913]
  Federated clustering addresses the challenge of extracting patterns from decentralized, unlabeled data.<n>We propose Structural Privacy-Preserving Federated Graph Clustering (SPP-FGC), a novel algorithm that innovatively leverages local structural graphs as the primary medium for privacy-preserving knowledge sharing.<n>Our framework achieves state-of-the-art performance, improving clustering accuracy by up to 10% (NMI) over federated baselines while maintaining provable privacy guarantees.
  arXiv  Detail & Related papers  (2025-11-14T03:05:22Z)
• Roleplaying with Structure: Synthetic Therapist-Client Conversation Generation from Questionnaires [5.163738939075784]
  We present an LLM-driven pipeline that generates synthetic counseling dialogues based on structured client profiles and psychological questionnaires.<n>Our framework, SQPsych, converts structured psychological input into natural language dialogues through therapist-client simulations.<n>Our findings highlight the potential of synthetic data to enable scalable, data-secure, and clinically informed AI for mental health support.
  arXiv  Detail & Related papers  (2025-10-29T10:55:52Z)
• MAGneT: Coordinated Multi-Agent Generation of Synthetic Multi-Turn Mental Health Counseling Sessions [58.61680631581921]
  We introduce MAGneT, a novel multi-agent framework for synthetic psychological counseling session generation.<n>Unlike prior single-agent approaches, MAGneT better captures the structure and nuance of real counseling.<n> Empirical results show that MAGneT significantly outperforms existing methods in quality, diversity, and therapeutic alignment of the generated counseling sessions.
  arXiv  Detail & Related papers  (2025-09-04T12:59:24Z)
• Cactus: Towards Psychological Counseling Conversations using Cognitive Behavioral Theory [24.937025825501998]
  We create a multi-turn dialogue dataset that emulates real-life interactions using the goal-oriented and structured approach of Cognitive Behavioral Therapy (CBT) We benchmark against established psychological criteria used to evaluate real counseling sessions, ensuring alignment with expert evaluations. Experimental results demonstrate that Camel, a model trained with Cactus, outperforms other models in counseling skills, highlighting its effectiveness and potential as a counseling agent.
  arXiv  Detail & Related papers  (2024-07-03T13:41:31Z)
• Personalized Federated Knowledge Graph Embedding with Client-Wise Relation Graph [49.66272783945571]
  We propose Personalized Federated knowledge graph Embedding with client-wise relation graph. PFedEG learns personalized supplementary knowledge for each client by amalgamating entity embedding from its neighboring clients. We conduct extensive experiments on four benchmark datasets to evaluate our method against state-of-the-art models.
  arXiv  Detail & Related papers  (2024-06-17T17:44:53Z)
• COCOA: CBT-based Conversational Counseling Agent using Memory Specialized in Cognitive Distortions and Dynamic Prompt [13.763448771196456]
  We develop a psychological counseling agent that applies Cognitive Behavioral Therapy (CBT) techniques to identify and address cognitive distortions inherent in the client's statements. We construct a memory system to efficiently manage information necessary for counseling while extracting high-level insights about the client.
  arXiv  Detail & Related papers  (2024-02-27T14:38:47Z)
• APGL4SR: A Generic Framework with Adaptive and Personalized Global Collaborative Information in Sequential Recommendation [86.29366168836141]
  We propose a graph-driven framework, named Adaptive and Personalized Graph Learning for Sequential Recommendation (APGL4SR) APGL4SR incorporates adaptive and personalized global collaborative information into sequential recommendation systems. As a generic framework, APGL4SR can outperform other baselines with significant margins.
  arXiv  Detail & Related papers  (2023-11-06T01:33:24Z)
• AUGUST: an Automatic Generation Understudy for Synthesizing Conversational Recommendation Datasets [56.052803235932686]
  We propose a novel automatic dataset synthesis approach that can generate both large-scale and high-quality recommendation dialogues. In doing so, we exploit: (i) rich personalized user profiles from traditional recommendation datasets, (ii) rich external knowledge from knowledge graphs, and (iii) the conversation ability contained in human-to-human conversational recommendation datasets.
  arXiv  Detail & Related papers  (2023-06-16T05:27:14Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.