본문 바로가기
KERD
논문KCI 등재

대규모 언어 모델에 기반한 정신치료: 마음이론 측면에서의 서술적 고찰

Psychotherapy Based on the Large Language Models: On the Aspect of the Theory of Mind, a Narrative Review

1

조회

0

다운로드

0

인용

0

참고문헌

키워드

주제분류정신과학

초록

This review evaluates the role of the large language model (LLM) in psychotherapy, emphasizing integration with theory of mind (ToM) and its influence on therapeutic outcomes and interactions. The current state-of-the-art in LLMs matches a 6-year-old’s ToM level, and thus encounters limitations in client interactions. Reinforcing the LLM ToM could improve interaction quality and can foster empathetic therapeutic settings vital for effective psychotherapy. However, significant gaps remain, especially in achieving contextual, human-like interactions. Key challenges include a lack of evaluation standards for LLM-based psychotherapies, insufficient clinical training data, and the need for a deeper exploration of therapeutic alliances between the LLM and the clients. This review emphasizes the transformative potential of the LLM in psychotherapy through integration with ToM, enhancing both the understanding of patients’ mental states and therapeutic interactions. Future research should focus on refining ToM benchmarks for the LLM, examining the therapeutic alliance, and addressing methodological issues to optimize ToM in LLM-based psychotherapy.

Abstract

This review evaluates the role of the large language model (LLM) in psychotherapy, emphasizing integration with theory of mind (ToM) and its influence on therapeutic outcomes and interactions. The current state-of-the-art in LLMs matches a 6-year-old’s ToM level, and thus encounters limitations in client interactions. Reinforcing the LLM ToM could improve interaction quality and can foster empathetic therapeutic settings vital for effective psychotherapy. However, significant gaps remain, especially in achieving contextual, human-like interactions. Key challenges include a lack of evaluation standards for LLM-based psychotherapies, insufficient clinical training data, and the need for a deeper exploration of therapeutic alliances between the LLM and the clients. This review emphasizes the transformative potential of the LLM in psychotherapy through integration with ToM, enhancing both the understanding of patients’ mental states and therapeutic interactions. Future research should focus on refining ToM benchmarks for the LLM, examining the therapeutic alliance, and addressing methodological issues to optimize ToM in LLM-based psychotherapy.

참고문헌 (128)

  1. "Mental-LLM: leveraging large language models for mental health prediction via online text data"[URL]
  2. Frith U, "Development and neurophysiology of mentalizing", Philos Trans R Soc Lond B Biol Sci, 358, pp.459~473 (2003)
  3. Wellman HM, "The child’s theory of mind" (1990), MIT Press
  4. Cologon J, "Therapist reflective functioning, therapist attachment style and therapist effectiveness", Adm Policy Ment Health, 44, pp.614~625 (2017)
  5. Stade EC, "Large language models could change the future of behavioral healthcare : a proposal for responsible development and evaluation", npj Mental Health Research, 3, pp.12~ (2024)
  6. Barnhart AJ, "Why ChatGPT means communication ethics problems for bioethics", Am J Bioeth, 23, pp.80~82 (2023)
  7. Fitzpatrick KK, "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, pp.e19~ (2017)
  8. Fulmer R, "Using psychological artificial intelligence(Tess)to relieve symptoms of depression and anxiety : randomized controlled trial", JMIR Ment Health, 5, pp.e64~ (2018)
  9. Li H, "Systematic review and meta-analysis of AI-based conversational agents for promoting mental health and well-being", NPJ Digit Med, 6, pp.236~ (2023)
  10. Hofmann SG, "The empirical status of the"new wave"of cognitive behavioral therapy", Psychiatr Clin North Am, 33, pp.701~710 (2010)
  11. Sabour S, "A chatbot for mental health support : exploring the impact of Emohaa on reducing mental distress in China", Front Digit Health, 5, pp.1133987~ (2023)
  12. Nazarova D, "Proceedings of the future technologies conference (FTC) 2023, volume 1", pp.204~219 (2023), Springer
  13. "Elomia chatbot: the effectiveness of artificial intelligence in the fight for mental health"[URL]
  14. Haley J, "Problem-solving therapy" (1992), Jossey-Bass
  15. Snyder WU, "An investigation of the nature of non-directive psychotherapy", J Gen Psychol, 33, pp.193~223 (1945)
  16. Nordgren I, E Svensson G, "Prompt engineering and its usability to improve modern psychology chatbots", Bachelor, pp.2023
  17. "Domain-specific assistant-instruction on psychotherapy chatbot"[URL]
  18. Bill D, Eriksson T, "Fine-tuning a LLM using reinforcement learning from human feedback for a therapy chatbot application", Bachelor, pp.2023
  19. "The power of scale for parameterefficient prompt tuning" (2021)[URL]
  20. Church KW, "Emerging trends : a gentle introduction to fine-tuning", Nat Lang Eng, 27, pp.763~778 (2021)
  21. Lambert MJ, "Research summary on the therapeutic relationship and psychotherapy outcome", Psychother Theory Res Pract Train, 38, pp.357~361 (2001)
  22. Holohan M, ""Like I’m talking to a real person" : exploring the meaning of transference for the use and design of AI-based applications in psychotherapy", Front Psychol, 12, pp.720476~ (2021)
  23. Montemayor C, "In principle obstacles for empathic AI : why we can’t replace human empathy in healthcare", AI Soc, 37, pp.1353~1359 (2022)
  24. Ellgring H, "Nonverbal expression of psychological states in psychiatric patients", Eur Arch Psychiatry Neurol Sci, 236, pp.31~34 (1986)
  25. Sedlakova J, "Conversational artificial intelligence in psychotherapy : a new therapeutic tool or agent?", Am J Bioeth, 23, pp.4~13 (2023)
  26. Bear Don’t Walk OJ 4th, "A scoping review of ethics considerations in clinical natural language processing", JAMIA Open, 5, pp.ooac039~ (2022)
  27. "Synthetic lies: understanding AI-generated misinformation and evaluating algorithmic and human solutions"[URL]
  28. Vaidyam AN, "Chatbots and conversational agents in mental health : a review of the psychiatric landscape", Can J Psychiatry, 64, pp.456~464 (2019)
  29. Denecke K, "Multiple perspectives on artificial intelligence in healthcare", pp.115~128 (2021), Springer
  30. "Do models of mental health based on social media data generalize?"[URL]
  31. Premack D, "Does the chimpanzee have a theory of mind?", Behav Brain Sci, 1, pp.515~526 (1978)
  32. Bartsch K, "Individual differences in children’s developing theory of mind and implications for metacognition", Learn Individ Differ, 8, pp.281~304 (1996)
  33. Watson AC, "Social interaction skills and theory of mind in young children", Dev Psychol, 35, pp.386~391 (1999)
  34. Happé FG, "An advanced test of theory of mind : understanding of story characters’ thoughts and feelings by able autistic, mentally handicapped, and normal children and adults", J Autism Dev Disord, 24, pp.129~154 (1994)
  35. Blanchard JJ, "Handbook of social functioning in schizophrenia", pp.181~196 (1998), Allyn & Bacon
  36. Baron-Cohen S, "Does the autistic child have a"theory of mind"?", Cognition, 21, pp.37~46 (1985)
  37. Bressi C, "Short-term psychodynamic psychotherapy with mentalization-based techniques in major depressive disorder patients : relationship among alexithymia, reflective functioning, and outcome variables–a pilot study", Psychol Psychother, 90, pp.299~313 (2017)
  38. Robinson P, "The NOURISHED randomised controlled trial comparing mentalisation-based treatment for eating disorders(MBT-ED)with specialist supportive clinical management(SSCM-ED)for patients with eating disorders and symptoms of borderline personality disorder", Trials, 17, pp.549~ (2016)
  39. Basharpoor S, "The effectiveness of mentalization-based therapy on emotional dysregulation and impulsivity in veterans with post-traumatic stress disorder", Neurosci J Shefaye Khatam, 8, pp.10~19 (2020)
  40. Wimmer H, "Beliefs about beliefs : representation and constraining function of wrong beliefs in young children’s understanding of deception", Cognition, 13, pp.103~128 (1983)
  41. Lewis C, "Three-year-olds’ problems with false belief : conceptual deficit or linguistic artifact?", Child Dev, 61, pp.1514~1519 (1990)
  42. Kinderman P, "Theory-of-mind deficits and causal attributions", Br J Psychol, 89, pp.191~204 (1998)
  43. Valle A, "Theory of mind development in adolescence and early adulthood : the growing complexity of recursive thinking ability", Eur J Psychol, 11, pp.112~124 (2015)
  44. Terentev M, "Emergent theory of mind in large language models", Bachelor, pp.2023
  45. Trott S, "Do large language models know what humans know?", Cogn Sci, 47, pp.e13309~ (2023)
  46. Bhola P, "Associations between countertransference reactions towards patients with borderline personality disorder and therapist experience levels and mentalization ability", Trends Psychiatry Psychother, 43, pp.116~125 (2021)
  47. Jones EE, "Therapeutic action : a guide to psychoanalytic therapy" (2000), Rowman & Littlefield
  48. Daubney M, "Mentalization-based therapy(MBT) : an overview", Australas Psychiatry, 23, pp.132~135 (2015)
  49. Anderson T, "Creative use of interpersonal skills in building a therapeutic alliance", J Constr Psychol, 12, pp.313~330 (1999)
  50. Anderson T, "Therapist effects : facilitative interpersonal skills as a predictor of therapist success", J Clin Psychol, 65, pp.755~768 (2009)
  51. Fonagy P, "The capacity for understanding mental states : the reflective self in parent and child and its significance for security of attachment", Infant Ment Health J, 12, pp.201~218 (1991)
  52. Reading RA, "Investigating therapist reflective functioning, therapeutic process, and outcome", Psychoanal Psychol, 36, pp.115~121 (2019)
  53. Ensink K, "The impact of mentalization training on the reflective function of novice therapists : a randomized controlled trial", Psychother Res, 23, pp.526~538 (2013)
  54. Bateman A, "Mentalization-based treatment", Psychoanal Inq, 33, pp.595~613 (2013)
  55. Malda-Castillo J, "Mentalization-based treatment and its evidence-base status : a systematic literature review", Psychol Psychother, 92, pp.465~498 (2019)
  56. Fonagy P, "Mechanisms of change in mentalizationbased treatment of BPD", J Clin Psychol, 62, pp.411~430 (2006)
  57. Bateman A, "Mentalization-based treatment for personality disorders: a practical guide" (2016), Oxford University Press
  58. Elliott R, "Therapist empathy and client outcome : an updated meta-analysis", Psychotherapy(Chic), 55, pp.399~410 (2018)
  59. Kaplowitz MJ, "Impact of therapist emotional intelligence on psychotherapy", J Nerv Ment Dis, 199, pp.74~84 (2011)
  60. Gratzer D, "Therapy and E-therapy—preparing future psychiatrists in the era of apps and chatbots", Acad Psychiatry, 44, pp.231~234 (2020)
  61. Elyoseph Z, "ChatGPT outperforms humans in emotional awareness evaluations", Front Psychol, 14, pp.1199058~ (2023)
  62. Hadar-Shoval D, "The plasticity of ChatGPT’s mentalizing abilities : personalization for personality structures", Front Psychiatry, 14, pp.1234397~ (2023)
  63. Cuijpers P, "Personalized psychotherapy for adult depression : a meta-analytic review", Behav Ther, 47, pp.966~980 (2016)
  64. Zilcha-Mano S, "Toward personalized psychotherapy : the importance of the trait-like", state-like distinction for understanding therapeutic change, 2021, pp.76, 516~528
  65. Luxton DD, "Artificial intelligence in behavioral and mental health care", pp.1~26 (2015), Academic Press
  66. Graesser AC, "Constructing inferences during narrative text comprehension", Psychol Rev, 101, pp.371~395 (1994)
  67. Mitchell M, "The debate over understanding in AI’s large language models", Proc Natl Acad Sci, 120, pp.e2215907120~ (2023)
  68. Phillips AT, "Infants’ ability to connect gaze and emotional expression to intentional action", Cognition, 85, pp.53~78 (2002)
  69. "Revisiting the evaluation of theory of mind through question answering"[URL]
  70. Elyoseph Z, "Capacity of generative AI to interpret human emotions from visual and textual data : pilot evaluation study", JMIR Ment Health, 11, pp.e54369~ (2024)
  71. Elyoseph Z, "Can large language models “read your mind in your eyes”?", JMIR Mental Health (2023)[DOI]
  72. Ma Z, "Understanding the benefits and challenges of using large language model-based conversational agents for mental well-being support", AMIA Annu Symp Proc, 2023, pp.1105~1114 (2023)
  73. "Task-adaptive tokenization: enhancing long-form text generation efficacy in mental health and beyond"[URL]
  74. Yang Y, "Multiturn dialogue generation by modeling sentence-level and discourse-level contexts", Sci Rep, 12, pp.20349~ (2022)
  75. "Chatbots and conversational agents in mental health: a literature review"[URL]
  76. Dang A, "Role of digital therapeutics and the changing future of healthcare", J Family Med Prim Care, 9, pp.2207~2213 (2020)
  77. Stade EC, "Large language models could change the future of behavioral healthcare : a proposal for responsible development and evaluation", Npj Ment Health Res, 3, pp.12~ (2024)
  78. Bantilan N, "Just in time crisis response : suicide alert system for telemedicine psychotherapy settings", Psychother Res, 31, pp.289~299 (2021)
  79. Alonso SG, "Data mining algorithms and techniques in mental health : a systematic review", J Med Syst, 42, pp.161~ (2018)
  80. Safranek CW, "The role of large language models in medical education : applications and implications", JMIR Med Educ, 9, pp.e50945~ (2023)
  81. He Y, "Mental health chatbot for young adults with depressive symptoms during the COVID-19 pandemic : single-blind, three-arm randomized controlled trial", J Med Internet Res, 24, pp.e40719~ (2022)
  82. Drouin M, "Is chatting with a sophisticated chatbot as good as chatting online or FTF with a stranger?", Comput Human Behav, 128, pp.107100~ (2022)
  83. Brunet-Gouet E, "Do conversational agents have a theory of mind? A single case study of ChatGPT with the hinting, false beliefs and false photographs, and strange stories paradigms", Zenodo (2023)[DOI]

이 간행물의 다른 논문 (4건)