RAG-TPC: Retrieval Augmented Generation for Teenager Psychological Counseling Using DeepSeek
DOI:
https://doi.org/10.4108/eetpht.11.11669Keywords:
Large Language Models, Retrieval Augmented Generation, DeepSeek, Fine-tuning, Psychological CounselingAbstract
The rising prevalence of adolescent mental health issues underscores the limitations of traditional counselling services in terms of scalability, timeliness, and accessibility. This paper presents RAG-TPC, a Retrieval-
Augmented Generation framework built upon the DeepSeek language model for teenage psychological counselling. The system incorporates intent classification, semantic retrieval, and structured prompt-based generation to produce safe, empathetic, and contextually appropriate responses. We construct a domain- specific dataset spanning general distress, mental illness, and SOS emergencies, and employ LoRA-based fine-tuning to enhance intent recognition. Experimental results show that RAG-TPC consistently outperforms competitive LLMs in both classification and response quality. Evaluations by psychological professionals further validate the system’s practical effectiveness and ethical reliability, highlighting its potential for scalable AI-assisted mental health support.
Downloads
References
[1] Hu E.J., Shen Y., Wallis P., Allen-Zhu Z., Li Y., Wang S., Wang L. and Chen W. et al. (2022) LoRA: Low-rank adaptation of large language models. (ICLR), 1(2), 3.
[2] Johnson J., Douze M. and Jegou H. (2021) Billion-Scale Similarity Search with GPUs (IEEE Transactions on Big Data), 7(03), 535–547.
[3] Shah H.A., Islam A., Tariq Z.U.A., Belhaouari S.B. and Househ M. (2025) Retrieval Augmented Generation System for Mental Health Information (in MedInfo 2025: Healthcare Smart x Medicine Deep, IOS Press), 693–697.
[4] VarastehNezhad A., Tavasoli R., Elyasi S., LotfiNia M.H. and Farbeh H. (2025) AI in Mental Health: Emotional and Sentiment Analysis of Large Language Models’ Responses to Depression, Anxiety, and Stress Queries (arXiv:2508.11285 [cs.CL]).
[5] Chen S., Liu Z., Zhang Z., Qin K., Qian Y. and Ma F. (2026) A cognitive-affective chain-driven framework for emotion understanding(Information Processing & Management), 63 (2, Part A), 104367.
[6] Li C. (2025) AIVA: An AI-based Virtual Companion for Emotion-aware Interaction (arXiv:2509.03212 [cs.CV]).
[7] Soman G., Judy M.V. and Abou A.M. (2025) Human guided empathetic AI agent for mental health support leveraging reinforcement learning-enhanced retrieval-augmented generation (Cognitive Systems Research), 90, 101337.
[8] Guu K., Lee K., Tung Z., Pasupat P. and Chang M.-W. (2020) REALM: Retrieval-Augmented Language Model Pre- Training (arXiv:2002.08909 [cs.CL]).
[9] Gao Y., Xiong Y., Gao X., Jia K., Pan J., Bi Y., Dai Y., Sun J., Wang M. and Wang H. (2024) Retrieval- Augmented Generation for Large Language Models: A Survey (arXiv:2312.10997 [cs.CL]).
[10] Lewis P., Perez E., Piktus A., Petroni F., Karpukhin V., Goyal N., Küttler H., Lewis M., Yih W.-t., Rocktäschel T., Riedel S. and Kiela D. (2021) Retrieval- Augmented Generation for Knowledge-Intensive NLP Tasks (arXiv:2005.11401[cs.CL]).
[11] Dong W., Liu Y., Bai R., Zhang L. and Zhou M. (2025) The prevalence and associated disability burden of mental disorders in children and adolescents in China: a systematic analysis of data from the Global Burden of Disease Study (The Lancet Regional Health–Western Pacific), 55.
[12] Reynolds L. and McDonell K. (2021) Prompt programming for large language models: Beyond the few-shot paradigm (in Extended abstracts of the 2021 CHI conference on human factors in computing systems), 1–7.
[13] Marvin G., Nakayiza H., Jjingo D. and Nakatumba- Nabende J. (2023) Prompt engineering in large language models (in International conference on data intelligence and cognitive informatics, Springer), 387–402.
[14] Nigh M. (2023) ChatGPT3-Free-Prompt-List: A free guide for learning to create ChatGPT3 Prompts https://github. com/mattnigh/ChatGPT3-Free-Prompt-List.
[15] Chen H. and Li Z. (2023) ChatGPT Advanced: An Introduction to Prompt Engineering (in ChatGPT Advanced: An Introduction to Prompt Engineering, Peking University Press, Beijing), 98–130 (in Chinese).
[16] Wang M., Liu Y., Liang X., Li S., Huang Y., Zhang X., Shen S., Guan C.,Wang D., Feng S. et al. (2024) LangGPT: Rethinking structured reusable prompt design framework for LLMs from the programming language (arXiv preprint arXiv:2402.16929).
[17] DukeManh (2023) Prompting Introduction https: //github.com/dair-ai/Prompt-Engineering-Guide/ blob/main/guides/prompts-intro.md, accessed 19 December 2024.
[18] Van Dijk D.A., Meijer R.M., van den Boogaard T.M., Spijker J., Ruhé H.G. and Peeters F.P.M.L. (2023) Worse off by waiting for treatment? The impact of waiting time on clinical course and treatment outcome for depression in routine care (Journal of Affective Disorders), 322, 205–211.
[19] Amin M.M., Cambria E. and Schuller B.W. (2023) Will affective computing emerge from foundation models and general artificial intelligence? A first evaluation of ChatGPT (IEEE Intelligent Systems), 38(2), 15–23.
[20] Ayers J.W., Poliak A., Dredze M., Leas E.C., Zhu Z., Kelley J.B., Faix D.J., Goodman A.M., Longhurst C.A., Hogarth M. and Smith D.M. (2023) Comparing Physician and Artificial Intelligence Chatbot Responses to Patient Questions Posted to a Public Social Media Forum (JAMA Internal Medicine), 183(6), 589–596.
[21] Das J.K., Salam R.A., Lassi Z.S., Khan M.N., Mahmood W., Patel V. and Bhutta Z.A. (2016) Interventions for Adolescent Mental Health: An Overview of Systematic Reviews (The Journal of Adolescent Health), 59(4S), S49– S60.
[22] Ma Z., Mei Y. and Su Z. (2024) Understanding the benefits and challenges of using large language model-based conversational agents for mental well-being support (in AMIA Annual Symposium Proceedings), 2023, 1105.
[23] Na H. (2024) CBT-LLM: A Chinese large language model for cognitive behavioral therapy-based mental health question answering (arXiv preprint arXiv:2403.16008).
[24] Chen D., Parsa R., Hope A., Hannon B., Mak E., Eng L., Liu F.-F., Fallah-rad N., Heesters A.M. and Raman S. (2024) Physician and artificial intelligence chatbot responses to cancer questions from social media (JAMA Oncology).
[25] Lai T., Shi Y., Du Z., Wu J., Fu K., Dou Y. and Wang Z. (2023) Psy-llm: Scaling up global mental health psychological services with ai-based large language models (arXiv preprint arXiv:2307.11991).
[26] De Choudhury M., Pendse S.R. and Kumar N. (2023) Benefits and harms of large language models in digital mental health (arXiv preprint arXiv:2311.14693).
[27] Elyoseph Z., Levkovich I. and Shinan-Altman S. (2024) Assessing prognosis in depression: comparing perspectives of AI models, mental health professionals and the general public (Family Medicine and Community Health), 12(Suppl 1), e002583.
[28] McCloud T., Jones R., Lewis G., Bell V. and Tsakanikos E. (2020) Effectiveness of a Mobile App Intervention for Anxiety and Depression Symptoms in University Students: Randomized Controlled Trial (JMIR mHealth and uHealth), 8(7), e15418.
[29] Habicht J., Viswanathan S., Carrington B., Hauser T., Harper R. and Rollwage M. (2023) Closing the accessibility gap to mental health treatment with a conversational aienabled self-referral tool(medRxiv).
[30] Wainberg M.L., Scorza P., Shultz J.M., Helpman L., Mootz J.J., Johnson K.A. and Arbuckle M.R. (2017) Challenges and opportunities in global mental health: a researchto- practice perspective (Current Psychiatry Reports), 19, 1– 10.
[31] Xu X., Yao B., Dong Y., Gabriel S., Yu H., Hendler J., Ghassemi M., Dey A.K. and Wang D. (2024) Mental- LLM: Leveraging Large Language Models for Mental Health Prediction via Online Text Data (Proceedings of the ACM on Interactive, Mobile, Wearable and Ubiquitous Technologies), 8(1), 1–32.
[32] Zhang Z. and Wang J. (2024) Can AI replace psychotherapists? Exploring the future of mental health care (Frontiers in Psychiatry), 15, 1444382.
[33] Zhong W., Luo J. and Zhang H. (2024) The therapeutic effectiveness of artificial intelligence-based chatbots in alleviation of depressive and anxiety symptoms in shortcourse treatments: A systematic review and meta-analysis (Journal of Affective Disorders).
[34] Ping Y. (2024) Experience in psychological counseling supported by artificial intelligence technology (Technology and Health Care), 32(6), 3871–3888.
[35] Cho Y., Kim M., Kim S., Kwon O., Kwon R.D., Lee Y. and Lim D. (2023) Evaluating the Efficacy of Interactive Language Therapy Based on LLM for High- Functioning Autistic Adolescent Psychological Counseling (arXiv preprint arXiv:2311.09243).
[36] World Health Organization (2021) WHO report highlights global shortfall in investment in mental health https://www.who.int/news/item/08-10-2021-whoreport- highlights-global-shortfall-in-investment-inmental-health
[37] Mahase E. (2020) Workforce crisis has left mental health staff at “breaking point” as demand rises (BMJ).
[38] Thornicroft G., Sunkel C., Aliev A.A., Baker S., Brohan E., el Chammay R., Davies K., Demissie M., Duncan J., Fekadu W., Gronholm P.C., Guerrero Z., Gurung D., Habtamu K., Hanlon C., Heim E., Henderson C., Hijazi Z., Hoffman C. and Winkler P. (2022) The Lancet Commission on ending stigma and discrimination in mental health(The Lancet), 400(10361), 1438–1480.
[39] Lee Y.-C., Cui Y., Jamieson J., Fu W. and Yamashita N. (2023) Exploring Effects of Chatbot-based Social Contact on Reducing Mental Illness Stigma(in Proceedings of the 2023 CHI Conference on Human Factors in Computing Systems, ACM), 1–16.
[40] Vespoli G., Taddei B., Imbimbo E., De Luca L. and Nocentini A. (2024) The concept of privacy in the digital world according to teenagers(Journal of Public Health).
[41] Towner E., Grint J., Levy T., Blakemore S.-J. and Tomova L. (2022) Revealing the self in a digital world: A systematic review of adolescent online and offline selfdisclosure( Current Opinion in Psychology), 45, 101309.
[42] McDonagh C., Lynch H. and Hennessy E. (2022) Do stigma and level of social anxiety predict adolescents’ help-seeking intentions for social anxiety disorder? (Early Intervention in Psychiatry), 16(4), 456–460.
[43] Wang H.L., Wu Z.Z. and Lang J.Y. (2020) Emotional First Aid Raw Datase thttps://github.com/chatopera/ efaqa-corpus-zh, accessed 22 April 2020.
[44] Ding N., Qin Y., Yang G., Wei F., Yang Z., Su Y., Hu S., Chen Y., Chan C.-M., Chen W. et al. (2023) Parameter-efficient fine-tuning of large-scale pre-trained language models (Nature Machine Intelligence), 5(3), 220– 235.
Downloads
Published
Issue
Section
License
Copyright (c) 2026 Yanling Li, Yibo Gao, Fangying Quan, Xudong Luo
This work is licensed under a Creative Commons Attribution-NonCommercial-ShareAlike 4.0 International License.
This is an open access article distributed under the terms of the CC BY-NC-SA 4.0, which permits copying, redistributing, remixing, transformation, and building upon the material in any medium so long as the original work is properly cited.
