PsyLite Technical Report

• URL: http://arxiv.org/abs/2506.21536v1
• Date: Thu, 26 Jun 2025 17:54:42 GMT
• Title: PsyLite Technical Report
• Authors: Fangjun Ding, Renyu Zhang, Xinyu Feng, Chengye Xie, Zheng Zhang, Yanting Zhang,
• Abstract summary: PsyLite is a lightweight psychological counseling large language model agent developed based on the base model InternLM2.5-7B-chat.<n>It enhances the model's deep-reasoning ability, psychological counseling ability, and safe dialogue ability.<n>A conditional RAG is designed to introduce crosstalk humor elements at appropriate times during psychological counseling to enhance user experience.
• Score: 6.7706541144197985
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: With the rapid development of digital technology, AI-driven psychological counseling has gradually become an important research direction in the field of mental health. However, existing models still have deficiencies in dialogue safety, detailed scenario handling, and lightweight deployment. To address these issues, this study proposes PsyLite, a lightweight psychological counseling large language model agent developed based on the base model InternLM2.5-7B-chat. Through a two-stage training strategy (hybrid distillation data fine-tuning and ORPO preference optimization), PsyLite enhances the model's deep-reasoning ability, psychological counseling ability, and safe dialogue ability. After deployment using Ollama and Open WebUI, a custom workflow is created with Pipelines. An innovative conditional RAG is designed to introduce crosstalk humor elements at appropriate times during psychological counseling to enhance user experience and decline dangerous requests to strengthen dialogue safety. Evaluations show that PsyLite outperforms the baseline models in the Chinese general evaluation (CEval), psychological counseling professional evaluation (CPsyCounE), and dialogue safety evaluation (SafeDialBench), particularly in psychological counseling professionalism (CPsyCounE score improvement of 47.6\%) and dialogue safety (\safe{} score improvement of 2.4\%). Additionally, the model uses quantization technology (GGUF q4\_k\_m) to achieve low hardware deployment (5GB memory is sufficient for operation), providing a feasible solution for psychological counseling applications in resource-constrained environments.

Related papers

• PsyProbe: Proactive and Interpretable Dialogue through User State Modeling for Exploratory Counseling [14.53071190134928]
  PsyProbe is a dialogue system designed for the exploration phase of counseling.<n>It tracks user psychological states through the PPPPPI framework.<n>It generates contextually appropriate, proactive questions.
  arXiv  Detail & Related papers  (2026-01-27T01:59:41Z)
• MindChat: A Privacy-preserving Large Language Model for Mental Health Support [10.332226758787277]
  We present MindChat, a privacy-preserving large language model for mental health support.<n>We also present MindCorpus, a synthetic multi-turn counseling dataset constructed via a multi-agent role-playing framework.
  arXiv  Detail & Related papers  (2026-01-05T10:54:18Z)
• TheraMind: A Strategic and Adaptive Agent for Longitudinal Psychological Counseling [53.46927050949822]
  We introduce TheraMind, a strategic and adaptive agent for longitudinal psychological counseling.<n>The cornerstone of TheraMind is a novel dual-loop architecture that decouples the counseling process into an Intra-Session Loop and a Cross-Session Loop.<n>The Cross-Session Loop empowers the agent with long-term adaptability by evaluating the efficacy of the applied therapy after each session and adjusting the method for subsequent interactions.
  arXiv  Detail & Related papers  (2025-10-29T17:54:20Z)
• Mentalic Net: Development of RAG-based Conversational AI and Evaluation Framework for Mental Health Support [0.0]
  Mentalic Net Conversational AI has a BERT Score of 0.898, with other evaluation metrics falling within satisfactory ranges.<n>We advocate for a human-in-the-loop approach and a long-term, responsible strategy in developing such transformative technologies.
  arXiv  Detail & Related papers  (2025-08-27T03:44:56Z)
• Reframe Your Life Story: Interactive Narrative Therapist and Innovative Moment Assessment with Large Language Models [92.93521294357058]
  Narrative therapy helps individuals transform problematic life stories into empowering alternatives.<n>Current approaches lack realism in specialized psychotherapy and fail to capture therapeutic progression over time.<n>Int (Interactive Narrative Therapist) simulates expert narrative therapists by planning therapeutic stages, guiding reflection levels, and generating contextually appropriate expert-like responses.
  arXiv  Detail & Related papers  (2025-07-27T11:52:09Z)
• AI PsyRoom: Artificial Intelligence Platform for Segmented Yearning and Reactive Outcome Optimization Method [8.268828460773028]
  Psychological counseling faces huge challenges due to the growing demand for mental health services and the shortage of trained professionals.<n>Large language models (LLMs) have shown potential to assist psychological counseling, especially in empathy and emotional support.<n>We present AI PsyRoom, a multi-agent simulation framework designed to enhance psychological counseling by generating empathetic and emotionally nuanced conversations.
  arXiv  Detail & Related papers  (2025-06-07T10:01:55Z)
• Beyond Empathy: Integrating Diagnostic and Therapeutic Reasoning with Large Language Models for Mental Health Counseling [17.809187205107232]
  PsyLLM is a large language model designed to integrate diagnostic and therapeutic reasoning for mental health counseling.<n>This pipeline processes real-world mental health posts and generates multi-turn dialogue structures.<n> Rigorous multi-dimensional filtering ensures the generation of high-quality, clinically aligned dialogue data.
  arXiv  Detail & Related papers  (2025-05-21T16:24:49Z)
• Ψ-Arena: Interactive Assessment and Optimization of LLM-based Psychological Counselors with Tripartite Feedback [51.26493826461026]
  We propose Psi-Arena, an interactive framework for comprehensive assessment and optimization of large language models (LLMs)<n>Arena features realistic arena interactions that simulate real-world counseling through multi-stage dialogues with psychologically profiled NPC clients.<n>Experiments across eight state-of-the-art LLMs show significant performance variations in different real-world scenarios and evaluation perspectives.
  arXiv  Detail & Related papers  (2025-05-06T08:22:51Z)
• PsyCounAssist: A Full-Cycle AI-Powered Psychological Counseling Assistant System [6.868956036918275]
  PsyCounAssist is a comprehensive AI-powered counseling system specifically designed to augment psychological counseling practices.<n>It integrates multimodal emotion recognition, automated structured session reporting, and personalized AI-generated follow-up support.<n> Deployed on Android-based tablet devices, the system demonstrates practical applicability and flexibility in real-world counseling scenarios.
  arXiv  Detail & Related papers  (2025-04-23T09:49:05Z)
• DeepPsy-Agent: A Stage-Aware and Deep-Thinking Emotional Support Agent System [10.262822400879688]
  DeepPsy-Agent is an innovative psychological support system that combines the three-stage helping theory in psychology with deep learning techniques.<n>Based on 30,000 real psychological hotline conversations, we employ AI-simulated dialogues and expert re-annotation strategies to construct a high-quality multi-turn dialogue dataset.
  arXiv  Detail & Related papers  (2025-03-20T05:59:29Z)
• AutoCBT: An Autonomous Multi-agent Framework for Cognitive Behavioral Therapy in Psychological Counseling [57.054489290192535]
  Traditional in-person psychological counseling remains primarily niche, often chosen by individuals with psychological issues.<n>Online automated counseling offers a potential solution for those hesitant to seek help due to feelings of shame.
  arXiv  Detail & Related papers  (2025-01-16T09:57:12Z)
• Enhancing AI-Driven Psychological Consultation: Layered Prompts with Large Language Models [44.99833362998488]
  We explore the use of large language models (LLMs) like GPT-4 to augment psychological consultation services. Our approach introduces a novel layered prompting system that dynamically adapts to user input. We also develop empathy-driven and scenario-based prompts to enhance the LLM's emotional intelligence.
  arXiv  Detail & Related papers  (2024-08-29T05:47:14Z)
• K-ESConv: Knowledge Injection for Emotional Support Dialogue Systems via Prompt Learning [83.19215082550163]
  We propose K-ESConv, a novel prompt learning based knowledge injection method for emotional support dialogue system. We evaluate our model on an emotional support dataset ESConv, where the model retrieves and incorporates knowledge from external professional emotional Q&A forum.
  arXiv  Detail & Related papers  (2023-12-16T08:10:10Z)
• JoTR: A Joint Transformer and Reinforcement Learning Framework for Dialog Policy Learning [53.83063435640911]
  Dialogue policy learning (DPL) is a crucial component of dialogue modelling. We introduce a novel framework, JoTR, to generate flexible dialogue actions. Unlike traditional methods, JoTR formulates a word-level policy that allows for a more dynamic and adaptable dialogue action generation.
  arXiv  Detail & Related papers  (2023-09-01T03:19:53Z)
• Modelling Hierarchical Structure between Dialogue Policy and Natural Language Generator with Option Framework for Task-oriented Dialogue System [49.39150449455407]
  HDNO is an option framework for designing latent dialogue acts to avoid designing specific dialogue act representations. We test HDNO on MultiWoz 2.0 and MultiWoz 2.1, the datasets on multi-domain dialogues, in comparison with word-level E2E model trained with RL, LaRL and HDSA.
  arXiv  Detail & Related papers  (2020-06-11T20:55:28Z)

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.