The Workshop on Computational Linguistics and Clinical Psychology

CLPsych, a workshop series founded in 2014

CLPsych 2026 will be held at ACL in San Diego

July 2 or 3, 2026

CLPsych 2025 Program

All times are in local time (New Mexico, MDT). Venue is the Tesuque/Zuni Suite, Albuquerque Convention Center.

8:45 AM	Workshop welcome & announcements (chairs: Ayah Zirikly, Andrew Yates)
8:55 AM	Keynote 1: Zohar Elyosef From Capabilities to Global Impact: Four Stations in AI Mental Health Research Abstract: This keynote examines generative artificial intelligence in mental health through four research stations: 1. Clinical Capabilities evaluates large language models’ performance with clinical vignettes across depression, anxiety, suicidality, and schizophrenia, analyzing diagnostic reasoning, treatment recommendations, and emotional recognition capabilities. 2. Organizational Components investigates structural elements shaping AI behavior, including embedded values, moral reasoning frameworks, and conformity tendencies. This research reveals how these models incorporate human-like organizing principles that fundamentally influence their clinical responses and decision-making processes. 3. Philosophical and Ethical Dimensions addresses conceptual frameworks for human-AI relationships, including “the artificial third” as a distinct therapeutic entity. This station explores mental health democratization through AI, theoretical foundations for AI-assisted psychotherapy, and the dynamics of anthropomorphization and technomorphization in human-machine interactions. 4. Scaling Mental Health Interventions demonstrates AI-based simulators for mentalization development, suicide risk assessment training, and tools promoting responsible suicide media coverage. This research shows how AI implementations can overcome service delivery barriers, creating accessible interventions that maintain therapeutic integrity while reaching underserved populations globally.
9:30 AM	Paper session 1 Topic: Measuring the Mind: Frontiers in AI-Based Mental Health Assessment Clinical discussant: Yaakov Ophir, PhD (Ariel University) Measuring Mental Health Variables in Computational Research: Toward Validated, Dimensional, and Transdiagnostic Approaches. Chen Shani and Elizabeth C. Stade Enhancing Depression Detection via Question-wise Modality Fusion. Aishik Mandal, Dana Atzil-Slonim, Thamar Solorio and Iryna Gurevych Linking Language-based Distortion Detection to Mental Health Outcomes. Vasudha Varadarajan, Allison Claire Lahnala, Sujeeth Anil Vankudari, Akshay Raghavan, Scott M. Feltman, Syeda Mahwish, Camilo Ruggero, Roman Kotov and H. Andrew Schwartz
10:30 AM	Coffee break
11:00 AM	Panel discussion Philip Resnik (University of Maryland) Sunny Tang (Northwell Health) Lyle Ungar (University of Pennsylvania) Steven Bedrick (moderator, Oregon Health & Science University)
12:00 PM	Shared task session Overview of the CLPsych 2025 Shared Task: Capturing Mental Health Dynamics from Social Media Timelines. Talia Tseriotou, Jenny Chim, Ayal Klein, Aya Shamir, Guy Dvir, Iqra Ali, Cian Kennedy, Guneet Singh Kohli, Anthony Hills, Ayah Zirikly, Dana Atzil-Slonim and Maria Liakata From Posts to Timelines: Modeling Mental Health Dynamics from Social Media Timelines with Hybrid LLMs. Zimu Wang, Hongbin Na, Rena Gao, Jiayuan Ma, Yining Hua, Ling Chen and Wei Wang Capturing the Dynamics of Mental Well-Being: Adaptive and Maladaptive States in Social Media. Anastasia Sandu, Teodor Mihailescu, Ana Sabina Uban and Ana-Maria Bucur From Evidence Mining to Meta-Prediction: a Gradient of Methodologies for Task-Specific Challenges in Psychological Assessment. Federico Ravenda, Fawzia-Zehra Kara-Isitt, Stephen Swift, Antonietta Mira and Andrea Raballo Prompt Engineering for Capturing Dynamic Mental Health Self States from Social Media Posts. Callum Chan, Sunveer Khunkhun, Diana Inkpen and Juan Antonio Lossio-Ventura
1:00 PM	Lunch break
2:15 PM	Keynote 2: Zac Imel Psychotherapy Research in the age of LLMS (or where did all the humans go?) Abstract: In his talk Zac will focus on revolutionary developments in the technology of psychotherapy science in the last decade, reviewing past and new contributions from his group and several others – particularly large scale evaluation of clinical conversations, the effects of machine learning supported training with automated feedback and simulated clients, and the dizzying prospect of a future psychotherapy research where clients, therapists, and raters are not necessarily human.
2:50 PM	Poster session
3:30 PM	Coffee break
4:00 PM	Paper session 2 Topic: Emotional capabilities of LLMs Clinical discussant: TBA AutoPsyC: Automatic Recognition of Psychodynamic Conflicts from Semi-structured Interviews with Large Language Models. Sayed Muddashir Hossain, Simon Ostermann, Patrick Gebhard, Cord Benecke, Josef van Genabith and Philipp Müller Assessing the Reliability and Validity of GPT-4 in Annotating Emotion Appraisal Ratings. Deniss Ruder, Andero Uusberg and Kairit Sirts The Emotional Spectrum of LLMs: Leveraging Empathy and Emotion-Based Markers for Mental Health Support. Alessandro De Grandi, Federico Ravenda, Andrea Raballo and Fabio Crestani
5:00 PM	Closing remarks
5:15 PM	Social dinner

Keynote Speakers

Dr. Zohar Elyoseph is an Associate Professor at the Department of Counseling and Human Development, Faculty of Education, University of Haifa. As a Specialist Educational Psychologist, his pioneering research focuses on the capabilities and applications of generative artificial intelligence in mental health, with emphasis on emotional recognition, clinical assessment, and suicide prevention. He has published extensively in prestigious journals, significantly contributing to the scientific literature examining large language models in mental health contexts. Dr. Elyoseph has developed innovative techniques for utilizing AI-based bots in clinical training, which have been adopted by researchers at leading institutions worldwide. Currently, he is constructing multi-agent systems to promote global mental health initiatives. Dr. Elyoseph serves as an academic advisor to Israel’s National AI Program in Education and co-founded “The Artificial Third,” a community of 5,000+ professionals advancing responsible AI applications in mental health. His research explores emotional intelligence frameworks in artificial systems and their implications for human-AI interaction.

Dr. Zac Imel‘s work has focused on the development and evaluation of machine learning technologies to improve the quality of mental health treatment. He trained at the University of Wisconsin-Madison and the Seattle VA, is a licensed psychologist, and currently Professor in the Counseling and Counseling Psychology Program in the Department of Educational Psychology and Adjunct Professor in the Department of Psychiatry at the University of Utah. Zac is also co-founder and Chief Science Officer of Lyssn.io – a technology company that develops and deploys machine learning technology to scale high quality mental healthcare for everyone. His work has been funded by NSF, NIMH, NIDA, NIAAA, PCORI, The John Templeton Foundation, and the Casey Foundation. He is co-author of a primary psychotherapy text, The Great Psychotherapy Debate: The Evidence for What Makes Psychotherapy Work – which offers a comprehensive review of the evidence for the effectiveness of psychotherapy.

Panelists

Dr. Philip Resnik is an MPower Professor at University of Maryland with joint appointments in the Department of Linguistics and the Institute for Advanced Computer Studies. He is one of the co-founders of CLPsych (along with Rebecca Resnik and Meg Mitchell). In 2020 he was designated a Fellow of the Association for Computational Linguistics. Philip’s most recent research has focused in two areas. One is the computational cognitive neuroscience of language, where he has been using computational modeling in connection with brain imaging to look at the role of context and predictive processing during online language comprehension. The other is computational social science, with an emphasis on connecting the signal available in people’s language use with underlying mental state, including applications in computational political science and in mental health.

Dr. Sunny Tang is an assistant professor of psychiatry at the Feinstein Institutes for Medical Research, Northwell Health, and the Zucker School of Medicine at Hofstra/Northwell. She is a board-certified psychiatrist, and her research expertise is in using speech and language markers for clinical applications in psychiatric disorders. Her work is supported by K and R21 awards from the National Institutes of Health, a Young Investigator Grant from the Brain and Behavior Research Foundation, and industry sponsors.

Dr. Lyle Ungar is a Professor of Computer and Information Science at the University of Pennsylvania, where he also holds secondary appointments in Psychology, Bioengineering, Genomics and Computational Biology, and Operations, Information and Decisions. His group uses natural language processing and explainable AI for psychological research, including analyzing social media and cell phone sensor data to better understand the drivers of physical and mental well-being and building socio-emotionally sensitive GPT-based tutors and coaches.

Dr. Steven Bedrick is an Associate Professor in Oregon Health & Science University’s Division of Medical Informatics, Clinical Epidemiology, and Translational Data Science. His work focuses on biomedical applications for speech and language technologies, including information retrieval, automatic speech recognition, and natural language processing. From a clinical perspective, he has two main areas of focus. First, speech and language disorders, including aphasia and Autism Spectrum Disorder; his work in this space focuses on computational tools for assessment and communication support. His second area of clinical focus is secondary use of clinical data, including electronic medical records, clinical trial protocols, and medical literature.