Elamur Research⌕
☰
home / papers / 2026 / PsyProbe: Proactive and Interpretable Dialogue through User State Modeling for Exploratory Counseling

PsyProbe: Proactive and Interpretable Dialogue through User State Modeling for Exploratory Counseling

Paper · 2026 · Sohhyung Park, Hyunji Kang, Sungzoon Cho et al.

Summary

LLM-based counseling assistants usually respond to what the user says instead of steering the conversation. This is a weakness in the exploration stage of counseling, whose goal is to uncover the problems behind a client's initial complaint. PsyProbe addresses this by keeping an explicit, evolving model of the user's psychological state. A State Builder detects cognitive distortions and fills the slots of an extended clinical formulation called PPPPPI (Presenting, Predisposing, Precipitating, Perpetuating, Protective, Impact) with textual evidence. It also infers the user's beliefs, desires and intent. A memory component records which slots are still unclear, and a Strategy Planner chooses Motivational Interviewing behavioral codes. The Response Generator then drafts questions aimed at those gaps and refines them through Critic/Revision loops. The authors tested the system with 27 participants in real Korean counseling sessions. PsyProbe outperformed a GPT baseline and its own ablations on automatic metrics and made users more willing to continue talking. A certified counselor judged that it asked questions about as often as human counselors and understood core issues much better. The results suggest that structured state tracking can make counseling dialogue more proactive and interpretable.

Key points

  • The user state combines four cognitive error categories (catastrophizing, overgeneralization, personalization, selective abstraction) with PPPPPI slots, adding an Impact dimension to the Five Ps. Selective abstraction is detected only through explicit "should/must" expressions.
  • The pipeline has four modules: State Builder, Memory Construction, Strategy Planner and Response Generator. It relies on multiple prompted LLM calls without fine-tuning, which the authors note may hurt latency and scalability.
  • In expert evaluation, Question Rate reached 0.815 for PsyProbe, compared with 0.263 for GPT and 0.830 for human counselors. Core Issue Understanding was 3.370 vs. 1.153 on a 5-point scale, and Probing Question Quality was 1.440 vs. 0.951.
  • Users reported an engagement-intention score of 1.19 for PsyProbe versus 0.33 for GPT, about 3.6× higher. Naturalness also improved, but empathy remains a weak spot.
  • Ablations show the State Builder and the Question Ideation + Critic/Revision modules contribute most. Limitations include 20-minute sessions, a small participant pool and coverage of the exploration phase only.

Our summary of the paper, in our own words — not its text. The work belongs to its authors; read it at the links above.

 Institutions

🎓Seoul National UniversitySeoul · South Korea41 works · 45,671 citations

 Fields, topics and concepts

📚 Shelves 7The field of science this work belongs to (OpenAlex fields).Computer Science · 16,667 worksArtificial Intelligence · 16,194 worksArts and Humanities · 16,039 worksLanguage and Linguistics · 15,891 worksPsychology · 1,552 worksExperimental and Cognitive Psychology · 870 worksApplied Psychology · 21 works

🧭 Topics 1Research subjects and languages the work is about.Dialogue systems · 624 works

Cite

Cite as Sohhyung Park, Hyunji Kang, Sungzoon Cho and Dongil Kim. 2026. PsyProbe: Proactive and Interpretable Dialogue through User State Modeling for Exploratory Counseling. Findings of the Association for Computational Linguistics: EACL 2026.

The paper itself, not this page. BibTeX from the library's record of the work. DOI 10.18653/v1/2026.findings-eacl.336

@inproceedings{park2026psyprobe,
  title = {{PsyProbe: Proactive and Interpretable Dialogue through User State Modeling for Exploratory Counseling}},
  author = {Sohhyung Park, Hyunji Kang, Sungzoon Cho and Dongil Kim},
  booktitle = {Findings of the Association for Computational Linguistics: EACL 2026},
  year = {2026},
  doi = {10.18653/v1/2026.findings-eacl.336},
  url = {https://doi.org/10.18653/v1/2026.findings-eacl.336}
}

References

38 references, 4 of them with a card of ours. ↗ leads to the work, «find» searches for one we have no id for yet.

  1. Josh Achiam, Steven Adler, Sandhini Agarwal, Lama Ahmad, Ilge Akkaya, Florencia Leoni Aleman, Diogo Almeida, Janko Altenschmidt, Sam Altman, Shyamal Anadkat, and 1 others. 2023. Gpt-4 technical report. arXiv preprint arXiv:2303.08774.
  2. Daniel Adiwardana, Minh-Thang Luong, David R. So, Jamie Hall, Noah Fiedel, Romal Thoppilan, Zi Yang, Apoorv Kulshreshtha, Gaurav Nemade, Yifeng Lu, and Quoc V. Le. 2020. Towards a human-like open-domain chatbot. CoRR, abs/2001.09977.
  3. Aaron T. Beck, A. John Rush, Brian F. Shaw, and Gary Emery. 1979. Cognitive therapy of depression. Guilford Press. find
  4. Emily Blake, Keith S. Dobson, Amanda R. Sheptycki, and Martin Drapeau. 2016. The relationship between depression severity and cognitive errors. American Journal of Psychotherapy, 70(2):203–221. PMID: 27329407. find
  5. Tom Brown, Benjamin Mann, Nick Ryder, Melanie Subbiah, Jared D Kaplan, Prafulla Dhariwal, Arvind Neelakantan, Pranav Shyam, Girish Sastry, Amanda Askell, Sandhini Agarwal, Ariel Herbert-Voss, Gretchen Krueger, Tom Henighan, Rewon Child, Aditya Ramesh, Daniel Ziegler, Jeffrey Wu, Clemens Winter, and… find
  6. Carlos Carona, Charlotte Handford, and Ana Fonseca. 2021. Socratic questioning put into clinical practice. BJPsych Advances, 27(6):424–426. find
  7. Maximillian Chen, Alexandros Papangelis, Chenyang Tao, Seokhwan Kim, Andy Rosenbaum, Yang Liu, Zhou Yu, and Dilek Hakkani-Tur. 2023. PLACES: Prompting language models for social conversation synthesis. In Findings of the Association for Computational Linguistics: EACL 2023, pages 844–868, Dubrovnik,…
  8. Kerstin Denecke, Alaa A. Abd-alrazaq, and Mowafa Said Househ. 2021. Artificial intelligence for chatbots in mental health: Opportunities and challenges. Multiple Perspectives on Artificial Intelligence in Healthcare. find
  9. Yang Deng, Wenxuan Zhang, Yifei Yuan, and Wai Lam. 2023. Knowledge-enhanced mixed-initiative dialogue system for emotional support conversations. Preprint, arXiv:2305.10172. find
  10. Albert Ellis. 1980. Rational-emotive therapy and cognitive behavior therapy: Similarities and differences. Cognitive Therapy and Research, 4(4):325–340. find
  11. American Psychiatric Association and 1 others. 2000. Diagnostic and statistical manual of mental disorders, text revision (dsm-iv-tr). find
  12. Kathleen Kara Fitzpatrick, Alison Darcy, and Molly Vierhile. 2017. Delivering cognitive behavior therapy to young adults with symptoms of depression and anxiety using a fully automated conversational agent (woebot): A randomized controlled trial. JMIR Ment Health, 4(2):e19. find
  13. Sanghwan Bae, Donghyun Kwak, Sungdong Kim, Donghoon Ham, Soyoung Kang, Sang-Woo Lee, and Woomyoung Park. 2022. Building a role specified open-domain dialogue system leveraging large-scale language models. arXiv preprint arXiv:2205.00176. find
  14. James Gibson, David C. Atkins, Torrey A. Creed, Zac Imel, Panayiotis Georgiou, and Shrikanth Narayanan. 2022. Multi-label multi-task deep learning for behavioral coding. IEEE Transactions on Affective Computing, 13(1):508–518. find
  15. Aaron T. Beck. 1976. Cognitive therapy and the emotional disorders. International Universities Press, Oxford, England. find
  16. Clara E. Hill. 2020. Helping skills: Facilitating exploration, insight, and action (5th ed.). American Psychological Association, Washington, DC. find
  17. Yuxin Hu, Danni Liu, Bo Liu, Yida Chen, Jiuxin Cao, and Yan Liu. 2025. PsyAdvisor: A plug-and-play strategy advice planner with proactive questioning in psychological conversations. In Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pa… find
  18. Hyunjong Kim, Suyeon Lee, Yeongjae Cho, Eunseo Ryu, Yohan Jo, Suran Seong, and Sungzoon Cho. 2025. KMI: A dataset of Korean motivational interviewing dialogues for psychotherapy. In Proceedings of the 2025 Conference of the Nations of the Americas Chapter of the Association for Computational Linguis… find
  19. Kurt Kroenke, Robert L. Spitzer, and Janet B. W. Williams. 2001. The phq-9. Journal of General Internal Medicine, 16(9):606–613. find
  20. Hannah R Lawrence, Renee A Schneider, Susan B Rubin, Maja J Matarić, Daniel J McDuff, and Megan Jones Bell. 2024. The opportunities and risks of large language models in mental health. JMIR Ment Health, 11:e59479. find
  21. Suyeon Lee, Hyejin Lee, Hyunjong Kim, Sohhyung Park, and Sungzoon Cho. 2025. PALbot+: An empathetic dialogue system for the marginalized populations in korea with AI safety features. In NAACL 2025 Workshop on Language Models for Underserved Communities. find
  22. Mark F. Lefebvre. 1981. Cognitive distortion and cognitive errors in depressed psychiatric and low back pain patients. Journal of Consulting and Clinical Psychology, 49(4):517–525. find
  23. Craig A. Macneil, Melissa K. Hasty, Philippe Conus, and Michael Berk. 2012. Is diagnosis enough to guide interventions in mental health? using case formulation in clinical practice. BMC Medicine, 10(1):111. find
  24. Fox, Iva Bojic, and 1 others. 2024. Advancing health coaching: A comparative study of large language model and health coaches. Artificial Intelligence in Medicine, 157:103004. find
  25. Verónica Pérez-Rosas, Rada Mihalcea, Kenneth Resnicow, Satinder Singh, Lawrence An, Kathy J. Goggin, and Delwyn Catley. 2017. Predicting counselor behaviors in motivational interviewing encounters. In Proceedings of the 15th Conference of the European Chapter of the Association for Computational Lin… find
  26. David Premack and Guy Woodruff. 1978. Does the chimpanzee have a theory of mind? Behavioral and Brain Sciences, 1(4):515–526. find
  27. Carl R. Rogers. 1957. The necessary and sufficient conditions of therapeutic personality change. Journal of Consulting Psychology, 21(2):95–103. find
  28. Carl Ransom Rogers and 1 others. 1959. A theory of therapy, personality, and interpersonal relationships: As developed in the client-centered framework, volume 3. McGraw-Hill New York. find
  29. Leili Tavabi, Trang Tran, Kalin Stefanov, Brian Borsari, Joshua Woolley, Stefan Scherer, and Mohammad Soleymani. 2021. Analysis of behavior classification in motivational interviewing. In Proceedings of the Seventh Workshop on Computational Linguistics and Clinical Psychology: Improving Access, page… find
  30. Niall Taylor, Andrey Kormilitzin, Isabelle Lorge, Alejo Nevado-Holgado, Andrea Cipriani, and Dan W Joyce. 2024. Model development for bespoke large language models for digital triage assistance in mental health care. Artificial Intelligence in Medicine, 157:102988. find
  31. T Bedirhan Üstün. 2010. Measuring health and disability: Manual for WHO disability assessment schedule WHODAS 2.0. World Health Organization. find
  32. Peter Muntigl and Adam O. Horvath. 2023. Strategic use of observer-perspective questions in couples therapy. Frontiers in Psychology, Volume 14 - 2023. find
  33. Jason Wei, Xuezhi Wang, Dale Schuurmans, Maarten Bosma, brian ichter, Fei Xia, Ed Chi, Quoc V Le, and Denny Zhou. 2022. Chain-of-thought prompting elicits reasoning in large language models. In Advances in Neural Information Processing Systems, volume 35, pages 24824–24837. Curran Associates, Inc.
  34. Kyo-Joong Oh, Dongkun Lee, Byungsoo Ko, and Ho-Jin Choi. 2017. A chatbot for psychiatric counseling in mental healthcare service based on emotional dialogue analysis and sentence generation. In 2017 18th IEEE International Conference on Mobile Data Management (MDM), pages 371–375. find
  35. Anuradha Welivita and Pearl Pu. 2023. Boosting distress support dialogue responses with motivational interviewing strategy. In Findings of the Association for Computational Linguistics: ACL 2023, pages 5411–5432, Toronto, Canada. Association for Computational Linguistics. find
  36. Qi Chwen Ong, Chin-Siang Ang, Davidson Zun Yin Chee, Ashwini Lawate, Frederick Sundram, Mayank Dalakoti, Leonardo Pasalic, Daniel To, Tatiana Erlikh Elizabeth Nutt Williams. 2023. The use of questions in psychotherapy: A review of research on immediate outcomes. Psychotherapy, 60(3):246–254. find
  37. William R. Miller and Stephen Rollnick. 2013. Motivational Interviewing: Helping People Change, 3 edition. Guilford Press, New York. find
  38. Aijia Yuan, Edlin Garcia Colato, Bernice Pescosolido, Hyunju Song, and Sagar Samtani. 2025. Improving workplace well-being in modern organizations: A review of large language model-based mental health chatbots. ACM Trans. Manage. Inf. Syst., 16(1). find

Updated

↑ back to top

This page in Markdown → https://md.research.elamur.ai/free/en/papers/park-2026-psyprobe-proactive-interpretable-dialogue-through/