A Survey of Large Language Models in Psychotherapy: Current Landscape and Future Directions
Not on the map. Why?
Abstract (arXiv)
Mental health is increasingly critical in contemporary healthcare, with psychotherapy demanding dynamic, context-sensitive interactions that traditional NLP methods struggle to capture. Large Language Models (LLMs) offer significant potential for addressing this gap due to their ability to handle extensive context and multi-turn reasoning. This review introduces a conceptual taxonomy dividing psychotherapy into interconnected stages--assessment, diagnosis, and treatment--to systematically examine LLM advancements and challenges. Our comprehensive analysis reveals imbalances in current research, such as a focus on common disorders, linguistic biases, fragmented methods, and limited theoretical integration. We identify critical challenges including capturing dynamic symptom fluctuations, overcoming linguistic and cultural biases, and ensuring diagnostic reliability. Highlighting future directions, we advocate for continuous multi-stage modeling, real-time adaptive systems grounded in psychological theory, and diversified research covering broader mental disorders and therapeutic approaches, aiming toward more holistic and clinically integrated psychotherapy LLMs systems.
Key facts. Cited by 12 papers in the map (data through 7 Oct 2026). Builds on 42 of its 108 references that are in the map. First posted on arXiv 16 Feb 2025.
Builds on
42 of 108 references.
References · 42
- 2023SoulChat: Improving LLMs' Empathy, Listening, and Comfort Abilities through Fine-tuning with Multi-turn Empathy Conversationscited by 109
- 2024CPsyCoun: A Report-based Multi-turn Dialogue Reconstruction and Evaluation Framework for Chinese Psychological Counselingcited by 88
- 2023Cognitive Reframing of Negative Thoughts through Human-Language Model Interactioncited by 77
- 2024Roleplay-doh: Enabling Domain-Experts to Create LLM-simulated Patients via Eliciting and Adhering to Principlescited by 72
- 2024A Computational Framework for Behavioral Assessment of LLM Therapistscited by 61
- 2024Cactus: Towards Psychological Counseling Conversations using Cognitive Behavioral Theorycited by 60
- 2024The opportunities and risks of large language models in mental healthcited by 54
- 2023Facilitating Self-Guided Mental Health Interventions Through Human-Language Model Interaction: A Case Study of Cognitive Restructuringcited by 53
- 2023MindfulDiary: Harnessing Large Language Model to Support Psychiatric Patients' Journalingcited by 50
- 2024HealMe: Harnessing Cognitive Reframing in Large Language Models for Psychotherapycited by 47
- 2024CBT-LLM: A Chinese Large Language Model for Cognitive Behavioral Therapy-based Mental Health Question Answeringcited by 45
- 2023When does In-context Learning Fall Short and Why? A Study on Specification-Heavy Taskscited by 37
30 more
- 2023Training Models to Generate, Recognize, and Reframe Unhelpful Thoughtscited by 31
- 2023Empowering Psychotherapy with Large Language Models: Cognitive Distortion Detection through Diagnosis of Thought Promptingcited by 31
- 2024PsychoGAT: A Novel Psychological Measurement Paradigm through Interactive Fiction Games with LLM Agentscited by 28
- 2023The Capability of Large Language Models to Measure Psychiatric Functioningcited by 25
- 2024LLM-based Conversational AI Therapist for Daily Functioning Screening and Psychotherapeutic Intervention via Everyday Smart Devicescited by 21
- 2024Multi-Level Feedback Generation with Large Language Models for Empowering Novice Peer Counselorscited by 16
- 2024Detecting Conversational Mental Manipulation with Intent-Aware Promptingcited by 16
- 2023Boosting Distress Support Dialogue Responses with Motivational Interviewing Strategycited by 15
- 2024ERD: A Framework for Improving LLM Reasoning for Cognitive Distortion Classificationcited by 14
- 2024Large Language Models are Capable of Offering Cognitive Reappraisal, if Guidedcited by 13
- 2024Depression Diagnosis Dialogue Simulation: Self-improving Psychiatrist with Tertiary Memorycited by 13
- 2024Diverse Perspectives, Divergent Models: Cross-Cultural Evaluation of Depression Detection on Twittercited by 12
- 2024Still Not Quite There! Evaluating Large Language Models for Comorbid Mental Health Diagnosiscited by 12
- 2024Document-level Causal Relation Extraction with Knowledge-guided Binary Question Answeringcited by 12
- 2024Knowledge Planning in Large Language Models for Domain-Aligned Counseling Summarizationcited by 11
- 2024WellDunn: On the Robustness and Explainability of Language Models and Large Language Models in Identifying Wellness Dimensionscited by 10
- 2024PsyGUARD: An Automated System for Suicide Detection and Risk Assessment in Psychological Counselingcited by 10
- 2024MentalAgora: A Gateway to Advanced Personalized Care in Mental Health through Multi-Agent Debating and Attribute Controlcited by 8
- 2024COCOA: CBT-based Conversational Counseling Agent using Memory Specialized in Cognitive Distortions and Dynamic Promptcited by 7
- 2024Aligning Large Language Models for Enhancing Psychiatric Interviews Through Symptom Delineation and Summarization: Pilot Studycited by 7
- 2024Zero-shot Explainable Mental Health Analysis on Social Media by Incorporating Mental Scalescited by 6
- 2024Detection and Positive Reconstruction of Cognitive Distortion sentences: Mandarin Dataset and Evaluationcited by 6
- 2024Generation, Distillation and Evaluation of Motivational Interviewing-Style Reflections with a Foundational Language Modelcited by 5
- 2024Multi-Session Client-Centered Treatment Outcome Evaluation in Psychotherapycited by 5
- 2024Taking a turn for the better: Conversation redirection throughout the course of mental-health therapycited by 5
- 2024Automating PTSD Diagnostics in Clinical Interviews: Leveraging Large Language Models for Trauma Assessmentscited by 4
- 2024We Care: Multimodal Depression Detection and Knowledge Infused Mental Health Therapeutic Response Generationcited by 4
- 2024Copiloting Diagnosis of Autism in Real Clinical Scenarios via LLMscited by 3
- 2024The Language of Trauma: Modeling Traumatic Event Descriptions Across Domains with Explainable AIcited by 2
- 2024Domain-specific Guided Summarization for Mental Health Postscited by 2
Built on by
Citing papers per year: 2025: 7; 2026: 5.
12 papers.
- 2025Expressing stigma and inappropriate responses prevents LLMs from safely replacing mental health providerscited by 67
- 2025Beyond Empathy: Integrating Diagnostic and Therapeutic Reasoning with Large Language Models for Mental Health Counselingcited by 17
- 2025Meaning Is Not A Metric: Using LLMs to make cultural context legible at scalecited by 10
- 2025Preference Learning Unlocks LLMs' Psycho-Counseling Skillscited by 9
- 2025Trustworthy AI Psychotherapy: Multi-Agent LLM Workflow for Counseling and Explainable Mental Disorder Diagnosiscited by 8
- 2025PsychiatryBench: A Multi-Task Benchmark for LLMs in Psychiatrycited by 6
- 2025Evolution of meta's llama models and parameter-efficient fine-tuning of large language models: a surveycited by 4
- 2026Auditing Stealth Sycophancy in Mental-Health Dialogue: Structured Clinical-State Diagnostics and Clean Matched Benchmarkscited by 1
- 2026DELTA: Deliberative Multi-Agent Reasoning with Reinforcement Learning for Multimodal Psychological Counselingcited by 0
- 2026Psy-Chronicle:A Structured Pipeline for Synthesizing Long-Horizon Campus Psychological Counseling Dialoguescited by 0
- 2026Information Dynamics of Language Communicationcited by 0
- 2026From Pattern Recognizers to Personalized Companions: A Survey of Large Language Models in Mental Healthcited by 0
- 2026From Pattern Recognizers to Personalized Companions: A Survey of Large Language Models in Mental Health21 Sep 2026
- 2026Information Dynamics of Language Communication29 Jun 2026
- 2026Psy-Chronicle:A Structured Pipeline for Synthesizing Long-Horizon Campus Psychological Counseling Dialogues21 May 2026
- 2026Auditing Stealth Sycophancy in Mental-Health Dialogue: Structured Clinical-State Diagnostics and Clean Matched Benchmarks5 May 2026
- 2026DELTA: Deliberative Multi-Agent Reasoning with Reinforcement Learning for Multimodal Psychological Counseling4 Feb 2026
- 2025Evolution of meta's llama models and parameter-efficient fine-tuning of large language models: a survey14 Oct 2025
- 2025PsychiatryBench: A Multi-Task Benchmark for LLMs in Psychiatry7 Sep 2025
- 2025Trustworthy AI Psychotherapy: Multi-Agent LLM Workflow for Counseling and Explainable Mental Disorder Diagnosis15 Aug 2025
- 2025Meaning Is Not A Metric: Using LLMs to make cultural context legible at scale23 May 2025
- 2025Beyond Empathy: Integrating Diagnostic and Therapeutic Reasoning with Large Language Models for Mental Health Counseling21 May 2025
- 2025Expressing stigma and inappropriate responses prevents LLMs from safely replacing mental health providers25 Apr 2025
- 2025Preference Learning Unlocks LLMs' Psycho-Counseling Skills27 Feb 2025