Research catalog

Publications on conversations with AI

Studies, reviews, datasets, and expert contributions on mental health, conversation quality, relationships, technology, law, and evaluation.

Publications: 500
Open access: 426
With DOI: 498
Period: 2017–2026

The catalog is built from bibliographic metadata provided by OpenAlex and verified primary sources, refreshed automatically on a regular schedule, then filtered by topic and deduplicated. Inclusion confirms topical fit, but is not a quality judgment; study design, source, and transferability remain decisive. Each publication has its own record, while automated working drafts and editorially reviewed analyses are clearly distinguished.

Data updated Oct 26, 2026

Sort

Publication typeYearOpen access only

500 publicationsBibliographic metadata from OpenAlex and verified primary sources · no automatic quality approval

Gepaarte Mehrdialog-Simulationen mit klinisch fundierten Personas und sechs LLMs zu Belastung, wahnhaftem Framing und Sicherheitsinterventionen2026Open Access

Law & ethics

Lost in Delusion: Examining LLM Safety Under User Delusions and Distress

Andrew Aquilina, Chetna Nihalani, Vasudha Varadarajan, Nathan S. Fishbein et al.

Proceedings of the 2026 Conference on Empirical Methods in Natural Language Processing

Wiederholte simulierte Interaktionen zur Prüfung von Chatbot-Antworten auf psychotische Vorstellungen2026

Therapy & mental health

Responses of large language model-based chatbots to simulated psychotic ideation across repeated interactions

Marek Kotas, Wojciech Pichowicz, Julia Karska, Kacper Żełabowski et al.

Schizophrenia Research

Simulations-, Ablations- und Expertenevaluation eines Rahmens für Emotionsverlaufsmodellierung und vorausschauende Risikoanalyse in Beratungsgesprächen2026Open Access

Conversation quality

PsychēChat: An Empathic Framework Focused on Emotion Shift Tracking and Safety Risk Analysis in Psychological Counseling

Zhentao Xia, Yongqi Fan, Yuxiang Chu, Yichao Yin et al.

Proceedings of the 2026 Conference on Empirical Methods in Natural Language Processing

Psychiatrische Vergleichsbewertung lokal betreibbarer koreanischer 7- bis 8-Milliarden-Modelle und GPT-4o zu Unterstützung, kultureller Angemessenheit und Sicherheit2026Open Access

Therapy & mental health

Optimizing Small Local Language Models for Culturally Competent Mental Health Counseling: Comparative Evaluation With GPT-4o by Psychiatrists

Jaewook Han, Beomgi So, Whanbo Jung, Minwoo Kim et al.

JMIR AI

Qualitative Interviews mit 18 Fachkräften zur situationsabhängigen ethischen Vertretbarkeit von KI in Einschätzung, Diagnose und Behandlung2026Open Access

Law & ethics

"There is a Place for it"-Practitioners' Perspectives on Situated Ethical Acceptability of AI Technologies for Mental Health Practice: Qualitative Study

Abeer Alotaibi, Corina Sas

JMIR Mental Health

Prospektive Implementierungsstudie mit menschlicher Prüfung und klinischer Eskalation2026Open Access

Law & ethics

Human-in-the-Loop Suicide Risk Detection and Clinical Escalation in a Generative AI Mental Health Chatbot: Prospective Implementation Study

Suzette Glasner, Darcy Michero, Matthew Stewart

JMIR Formative Research

Mehrdialog-Datensatz und Evaluationsrahmen mit mehr als 2.200 synthetischen Patient-LLM-Gesprächen2026Open Access

Conversation quality

Reasoning Is Not All You Need: Examining LLMs for Multi-Turn Mental Health Conversations

Mohit Chandra, Siddharth Sriraman, Harneet Singh Khanuja, Yiqiao Jin et al.

Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)

Scoping Review zu 23 Projekten mit Fokus auf Unterstützungsfunktionen, Evaluation, Aufsicht, Kriseneskalation und KI-Kennzeichnung2026Open Access

Therapy & mental health

Mapping Technologies, Support Functions, Evaluation Outcomes, and Safety Governance Related to Conversational AI Agents for Psychological Support of Patients With Cancer: Scoping Review

Zhiying Shen, Shuangjiao Shi, Lian Mao, Chengyuan Li et al.

Journal of Medical Internet Research

Rollenbewusste mehrdialogische Sicherheitsevaluation mit adversarialen Interaktionsverläufen2026Open Access

Law & ethics

MHSafeEval: Role-Aware Interaction-Level Evaluation of Mental Health Safety in Large Language Models

Suhyun Lee, Palakorn Achananuparp, Neemesh Yadav, Ee-Peng Lim et al.

Findings of the Association for Computational Linguistics: ACL 2026

Beobachtende vergleichende Querschnittsstudie zu Suizidantworten von API- und Endnutzer-Chatbots2026Open Access

Law & ethics

Suicide-Related Responses From AI Chatbots Through Application Programming Interfaces and Consumer-Facing Apps: Observational Cross-Sectional Comparative Study

Jonathan Cantor, Ellice Huang, Li Ang Zhang, Adrian Salas et al.

Journal of Medical Internet Research

Simulationsstudie wiederholter Interaktionen mit eskalierendem Suizidrisiko2026

Law & ethics

Responses of AI chatbots to escalating suicide risk: A simulation study of repeated interactions

Wojciech Pichowicz, Marek Kotas, Natalia Kalka, Julia Dembowska et al.

Journal of Affective Disorders

Methodischer Rahmen für Entwicklung und Prüfung eines LLM-basierten virtuellen Begleiters bei sozial isolationsgefährdeten älteren Menschen2026

Relationship & impact

A Methodological Framework for a Large Language Model Virtual Companion for Older Adults at Risk of Social Isolation

Haichao Yao

Journal of Visualized Experiments

Präregistrierte randomisierte kontrollierte Studie mit 977 Studierenden und Drei-Monats-Nachbeobachtung2026Open Access

Therapy & mental health

Attachment, loneliness, and social support as moderators of conversational AI-based mental health outcomes

Anat Shoshani, Bar Gurfinkel, Ariel Kor, Or Kanarek et al.

npj Digital Medicine

Theoretische Einordnung dazu, wie dialogische KI zeitliche Rhythmen und Bedingungen von Selbstreflexion verändert2026

Conversation quality

Conversational AI and the Temporal Ecology of Self-Reflection

Dana Kvietkute

Integrative Psychological & Behavioral Science

Querschnittsbefragung zum Hilfesuchverhalten nach Marktrücknahme eines spezialisierten KI-Wohlbefindenswerkzeugs2026Open Access

Relationship & impact

Support-Seeking After Market Withdrawal of a Purpose-Built AI Well-Being Tool (Ash): Cross-Sectional Survey

Caitlin A. Stamatis, Kaylee P. Kruzan, Josh Hsu, Mark A. Ungless et al.

JMIR Medical Informatics

Qualitative Interviewstudie mit 20 Personen mit psychischen Erkrankungen und LLM-Nutzung2026Open Access

Relationship & impact

A Conditional Companion: Lived Experiences of People with Mental Health Disorders Using LLMs

Aditya Kumar Purohit, Hendrik Heuer

Proceedings of the 2026 CHI Conference on Human Factors in Computing Systems

Psychometrischer Fünf-Domänen-Rahmen zur Prüfung LLM-abgeleiteter psychologischer Messwerte2026Open Access

Tests & data

Evaluating Large Language Model-Derived Outputs as Psychological Measures: A Five-Domain Psychometric Framework With Application to Daily Stress

Inyong Jeong, Soohyun Park, Min Jhon, Dae-Kwang Kim et al.

Journal of Medical Internet Research

Randomisierte kontrollierte Studie zu Machbarkeit, Akzeptanz und vorläufiger Wirksamkeit einer mobilen CBT-Intervention2026Open Access

Therapy & mental health

Woebot for Postpartum Mood and Anxiety: Randomized Controlled Trial Evaluating Feasibility, Acceptability, and Preliminary Efficacy of a Mobile Cognitive Behavioral Therapy Intervention

Toluwalase Ajayi, Jacqueline Kueper, Jill Waalen, Lauren Ariniello et al.

JMIR Pediatrics and Parenting

Vergleich von Generierung und leitliniengestütztem RAG anhand anonymisierter CBT-Rollenspielsitzungen2026Open Access

Therapy & mental health

Assessing the Effectiveness of LLMs in Delivering Cognitive Behavioral Therapy

Navdeep Singh Bedi, Ana-Maria Bucur, Noriko Kando, Fabio Crestani

Proceedings of the Fifteenth Language Resources and Evaluation Conference

Systemdemonstration und formative Studie zur psychosozialen Sicherheitsprüfung von LLM-Antworten2026Open Access

Models & technology

DialogGuard: Multi-Agent Psychosocial Safety Evaluation Interface of Sensitive LLM Responses

Han Luo, Guy Laban

Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 3: System Demonstrations)

Metaanalyse von 35 Studien mit 1.780 Teilnehmenden2026

Therapy & mental health

Predicting Symptom Change in Mental Health Chatbot Interventions: A Meta-Analysis

Camille J. Saucier, Huaye Li, Christopher Calabrese, Anna Baker et al.

Health Communication

Querschnittliche Mixed-Methods-Analyse in einer deutschen psychotherapeutischen Hochschulambulanz2026Open Access

Therapy & mental health

Use of Generic Large Language Model Chatbots for Mental Health Issues Among Patients Seeking Psychotherapy: Cross-Sectional Mixed Methods Analysis in a German University Hospital Outpatient Clinic

Alexander Diel, Niels Weber, Jil Beckord, Tania Lalgi et al.

JMIR AI

Europäische rechtswissenschaftliche und klinische Einordnung von Haftung und Sorgfaltsstandard2026Open Access

Law & ethics

Liability and Standard of Care in AI-Driven Psychiatric Practice: European Viewpoint

Luis Madeira, Cíntia Águas, Meryam Schouler-Ocak, Jerzy Samochowiec et al.

Journal of Medical Internet Research

Empirische Studie zu Einsamkeit, emotionaler Bindung, Eskapismus und Nutzungsabsicht bei KI-Begleiter-Apps2026Open Access

Relationship & impact

Loneliness to consumption intention: emotional bonding and escapism in AI emotional companion app use

Pei Yao, Zirong Tian, Jongmoo Kim

Frontiers in Public Health

Persona-basierte Mehrdialog-Sicherheitsevaluation mit 1.674 Dialogpaaren2026Open Access

Law & ethics

Persona-Grounded Safety Evaluation of AI Companions in Multi-Turn Conversations

Prerna Juneja, Lika Lomidze

Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)

Interdisziplinärer Evaluationsrahmen und Analyse von 135 Publikationen2026Open Access

Law & ethics

Responsible Evaluation of AI for Mental Health

Hiba Arnaout, Anmol Goel, H. Andrew Schwartz, Steffen T. Eberhardt et al.

Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)

Qualitative Fokusgruppenstudie mit Menschen mit schweren psychischen Erkrankungen2026

Relationship & impact

Perspectives of People with Serious Mental Illness on Artificial Intelligence-Based Companions: "If no one told you I love you today, you have someone that cares for you."

Vedant Tapiavala, Sai S. Chilakapati, Dylan Moore, Shamika Morales et al.

Community Mental Health Journal

Qualitativ dominierte Mixed-Methods-Studie zu KI-Begleitung als relationale Ergänzung2026Open Access

Relationship & impact

Artificial Intelligence as Companionship: A Systemic and Relational Examination Using Empirical Data From Psyhelp

Afarin Rajaei

Journal of Marital and Family Therapy

Systematische Übersicht und Rahmen für die Bewertung vor dem Einsatz2026

Law & ethics

Toward a Framework for Assessing Patient-Facing Gen AI Tools in Mental Healthcare

Polina Durneva, Hedieh Ghorbanie

International Journal of Medical Informatics

PRISMA-ScR-Scoping-Review zu KI-gestützten und vergleichbaren digitalen Interventionen für Jugendliche2026Open Access

Therapy & mental health

AI-enabled and comparator digital interventions for adolescent mental health (2020-2025): early detection, human-AI collaboration, and ethical governance-a PRISMA-ScR scoping review

Noorayisahbe Mohd Yaacob, Mohamed Doheir, Ali Algumaei, Mohammed Nasser Al-Andoli et al.

Frontiers in Child and Adolescent Psychiatry