mlsanityData to 14 Oct 2026

Trust Stack for Mental Health AI: A Survey of Calibration across Human, Interaction, and AI Layers

arXiv 2604.20166 ↗First posted 22 Apr 2026cs.CL cs.HCcited by 0

Not on the map. Why?

Abstract (arXiv)

Language-based AI is increasingly deployed for mental health support, yet trust is evaluated in interdisciplinary but operationally misaligned ways: NLP and AI work measures robustness, safety, privacy, and explanations, while psychotherapy, HCI, and regulatory work emphasize therapeutic fidelity, lived experience, empathy, and reliance. Empathetic chatbots can elicit strong user trust without commensurate safety, while safer systems are under-trusted when their boundaries are opaque, a calibration gap no single community owns. Through a structured scoping synthesis of 61 papers, we survey this landscape into a three-layer framework separating (L1) human-oriented trust, (L2) interaction-oriented trustworthiness, and (L3) AI-oriented trustworthiness, and map five stakeholder perspectives onto these layers. We outline a research agenda for building socio-technically aligned trustworthy AI for mental health support, highlighting that the central objective should shift from maximizing perceived trust to calibrating human trust to demonstrated interaction- and AI-level trustworthiness.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 27 of its 82 references that are in the map. First posted on arXiv 22 Apr 2026.

Builds on

27 of 82 references.

References · 27

  1. 2023DecodingTrust: A Comprehensive Assessment of Trustworthiness in GPT Modelscited by 518
  2. 2023Trustworthy LLMs: a Survey and Guideline for Evaluating Large Language Models' Alignmentcited by 401
  3. 2020Formalizing Trust in Artificial Intelligence: Prerequisites, Causes and Goals of Human Trust in AIcited by 167
  4. 2023SoulChat: Improving LLMs' Empathy, Listening, and Comfort Abilities through Fine-tuning with Multi-turn Empathy Conversationscited by 110
  5. 2024PsySafe: A Comprehensive Framework for Psychological-based Attack, Defense, and Evaluation of Multi-agent System Safetycited by 80
  6. 2024TrustAgent: Towards Safe and Trustworthy LLM-based Agentscited by 64
  7. 2022Designing for Responsible Trust in AI Systems: A Communication Perspectivecited by 48
  8. 2025Customizing Emotional Support: How Do Individuals Construct and Interact With LLM-Powered Chatbotscited by 25
  9. 2025EmoAgent: Assessing and Safeguarding Human-AI Interaction for Mental Health Safetycited by 21
  10. 2025AnnaAgent: Dynamic Evolution Agent System with Multi-Session Memory for Realistic Seeker Simulationcited by 21
  11. 2024The Colorful Future of LLMs: Evaluating and Improving LLMs as Emotional Supporters for Queer Youthcited by 20
  12. 2024Understanding the Therapeutic Relationship between Counselors and Clients in Online Text-based Counseling using LLMscited by 19
15 more
  1. 2023An Integrative Survey on Mental Health Conversational Agents to Bridge Computer Science and Medical Perspectivescited by 16
  2. 2024Writing Style Matters: An Examination of Bias and Fairness in Information Retrieval Systemscited by 15
  3. 2025MAGI: Multi-Agent Guided Interview for Psychiatric Assessmentcited by 14
  4. 2025KokoroChat: A Japanese Psychological Counseling Dialogue Dataset Collected via Role-Playing by Trained Counselorscited by 13
  5. 2025Exploring User Security and Privacy Attitudes and Concerns Toward the Use of General-Purpose LLM Chatbots for Mental Healthcited by 13
  6. 2024Knowledge Planning in Large Language Models for Domain-Aligned Counseling Summarizationcited by 11
  7. 2023FedTherapist: Mental Health Monitoring with User-Generated Linguistic Expressions on Smartphones via Federated Learningcited by 10
  8. 2024Private Yet Social: How LLM Chatbots Support and Challenge Eating Disorder Recoverycited by 8
  9. 2025Trustworthy AI Psychotherapy: Multi-Agent LLM Workflow for Counseling and Explainable Mental Disorder Diagnosiscited by 8
  10. 2024Assessment and manipulation of latent constructs in pre-trained language models using psychometric scalescited by 7
  11. 2024Script-Strategy Aligned Generation: Aligning LLMs with Expert-Crafted Dialogue Scripts and Therapeutic Strategies for Psychotherapycited by 7
  12. 2025Understanding Attitudes and Trust of Generative AI Chatbots for Social Anxiety Supportcited by 5
  13. 2025Position: Beyond Assistance -- Reimagining LLMs as Ethical and Adaptive Co-Creators in Mental Health Carecited by 3
  14. 2022The Impact of Explanations on Layperson Trust in Artificial Intelligence-Driven Symptom Checker Apps: Experimental Studycited by 2
  15. 2025Understanding Adolescents' Perceptions of Benefits and Risks in Health AI Technologies through Design Fictioncited by 2

Built on by

Not cited yet.