Constructing a Knowledge-Guided Mental Health Chatbot with LLMs

Xi Fan, Lishan Yang, Xiangyu Wang, Derui Lyu, Huanhuan Chen
Proceedings of the 16th Asian Conference on Machine Learning, PMLR 260:287-302, 2025.

Abstract

The global shortage of mental health resources has severely impacted the ability to address psychological distress, affecting approximately 658 million people. Despite the effectiveness of psychotherapy and counseling, less than 35% of those in need receive help. Traditional conversational agents often lack emotional support, leading to mechanical interactions that detract from user experience. This paper introduces the "Mental Health Chatbot," a conversational agent based on a pre-trained large language model. This chatbot innovatively uses retrieval-augmentation techniques to extract relevant knowledge from psychological diagnostics and treatment manuals, providing tailored psychotherapeutic interventions. It effectively identifies mental disorders and their severity, suggesting appropriate interventions. Evaluated through pre-trained model similarity comparisons, large language model scoring, and expert assessments, results show that the Mental Health Chatbot enhances the accuracy of smaller models and accelerates the inference speed of larger models through retrieval-augmentation. The optimized training process enables more human-like interactions, improving user experience and demonstrating the chatbot’s potential and practical application in addressing mental health challenges.

Cite this Paper

BibTeX
@InProceedings{pmlr-v260-fan25a, title = {Constructing a Knowledge-Guided Mental Health Chatbot with LLMs}, author = {Fan, Xi and Yang, Lishan and Wang, Xiangyu and Lyu, Derui and Chen, Huanhuan}, booktitle = {Proceedings of the 16th Asian Conference on Machine Learning}, pages = {287--302}, year = {2025}, editor = {Nguyen, Vu and Lin, Hsuan-Tien}, volume = {260}, series = {Proceedings of Machine Learning Research}, month = {05--08 Dec}, publisher = {PMLR}, pdf = {https://raw.githubusercontent.com/mlresearch/v260/main/assets/fan25a/fan25a.pdf}, url = {https://proceedings.mlr.press/v260/fan25a.html}, abstract = {The global shortage of mental health resources has severely impacted the ability to address psychological distress, affecting approximately 658 million people. Despite the effectiveness of psychotherapy and counseling, less than 35% of those in need receive help. Traditional conversational agents often lack emotional support, leading to mechanical interactions that detract from user experience. This paper introduces the "Mental Health Chatbot," a conversational agent based on a pre-trained large language model. This chatbot innovatively uses retrieval-augmentation techniques to extract relevant knowledge from psychological diagnostics and treatment manuals, providing tailored psychotherapeutic interventions. It effectively identifies mental disorders and their severity, suggesting appropriate interventions. Evaluated through pre-trained model similarity comparisons, large language model scoring, and expert assessments, results show that the Mental Health Chatbot enhances the accuracy of smaller models and accelerates the inference speed of larger models through retrieval-augmentation. The optimized training process enables more human-like interactions, improving user experience and demonstrating the chatbot’s potential and practical application in addressing mental health challenges.} }
Endnote
%0 Conference Paper %T Constructing a Knowledge-Guided Mental Health Chatbot with LLMs %A Xi Fan %A Lishan Yang %A Xiangyu Wang %A Derui Lyu %A Huanhuan Chen %B Proceedings of the 16th Asian Conference on Machine Learning %C Proceedings of Machine Learning Research %D 2025 %E Vu Nguyen %E Hsuan-Tien Lin %F pmlr-v260-fan25a %I PMLR %P 287--302 %U https://proceedings.mlr.press/v260/fan25a.html %V 260 %X The global shortage of mental health resources has severely impacted the ability to address psychological distress, affecting approximately 658 million people. Despite the effectiveness of psychotherapy and counseling, less than 35% of those in need receive help. Traditional conversational agents often lack emotional support, leading to mechanical interactions that detract from user experience. This paper introduces the "Mental Health Chatbot," a conversational agent based on a pre-trained large language model. This chatbot innovatively uses retrieval-augmentation techniques to extract relevant knowledge from psychological diagnostics and treatment manuals, providing tailored psychotherapeutic interventions. It effectively identifies mental disorders and their severity, suggesting appropriate interventions. Evaluated through pre-trained model similarity comparisons, large language model scoring, and expert assessments, results show that the Mental Health Chatbot enhances the accuracy of smaller models and accelerates the inference speed of larger models through retrieval-augmentation. The optimized training process enables more human-like interactions, improving user experience and demonstrating the chatbot’s potential and practical application in addressing mental health challenges.
APA
Fan, X., Yang, L., Wang, X., Lyu, D. & Chen, H.. (2025). Constructing a Knowledge-Guided Mental Health Chatbot with LLMs. Proceedings of the 16th Asian Conference on Machine Learning, in Proceedings of Machine Learning Research 260:287-302 Available from https://proceedings.mlr.press/v260/fan25a.html.

Related Material