Artificial intelligence has been introduced as a way to improve access to mental health support. However, most AI mental health chatbots rely on a limited range of disciplinary input, and fail to integrate expertise across the chatbot's lifecycle. This paper examines the cost-benefit trade-off of interdisciplinary collaboration in AI mental health chatbots. We argue that involving experts from technology, healthcare, ethics, and law across key lifecycle phases is essential to ensure value-alignment and compliance with the high-risk requirements of the AI Act. We also highlight practical recommendations and existing frameworks to help balance the challenges and benefits of interdisciplinarity in mental health chatbots.

We present TheraGen, an advanced AI-powered mental health chatbot utilizing the LLaMA 2 7B model. This approach builds upon recent advancements in language models and transformer architectures. TheraGen provides all-day personalized, compassionate mental health care by leveraging a large dataset of 1 million conversational entries, combining anonymized therapy transcripts, online mental health discussions, and psychological literature, including APA resources. Our implementation employs transfer learning, fine-tuning, and advanced training techniques to optimize performance. TheraGen offers a user-friendly interface for seamless interaction, providing empathetic responses and evidence-based coping strategies. Evaluation results demonstrate high user satisfaction rates, with 94% of users reporting improved mental well-being. The system achieved a BLEU score of 0.67 and a ROUGE score of 0.62, indicating strong response accuracy. With an average response time of 1395 milliseconds, TheraGen ensures real-time, efficient support. While not a replacement for professional therapy, TheraGen serves as a valuable complementary tool, significantly improving user well-being and addressing the accessibility gap in mental health treatments. This paper details TheraGen's architecture, training methodology, ethical considerations, and future directions, contributing to the growing field of AI-assisted mental healthcare and offering a scalable solution to the pressing need for mental health support.

Key Words: Mental health chatbots, large language models, clinical safety, evaluation metrics, automated assessment Word Count: 3,686 ABSTRACT Objective: This study aims to develop and validate an evaluation framework to ensure the safety and reliability of mental health chatbots, which are increasingly popular due to their accessibility, human-like interactions, and context-aware support. Materials and Methods: We created an evaluation framework with 100 benchmark questions and ideal responses, and five guideline questions for chatbot responses. This framework, validated by mental health experts, was tested on a GPT-3.5-turbo-based Automated evaluation methods explored included large language model (LLM)-based scoring, an agentic approach using real-time data, and embedding models to compare chatbot responses against ground truth standards. The agentic method, dynamically accessing reliable information, demonstrated the best alignment with human assessments. Discussion: Our findings emphasize the need for comprehensive, expert-tailored safety evaluation metrics for mental health chatbots. While LLMs have significant potential, careful implementation is necessary to mitigate risks. The superior performance of the agentic approach underscores the importance of real-time data access in enhancing chatbot reliability. Future work should extend evaluations to accuracy, bias, empathy, and privacy to ensure holistic assessment and responsible integration into healthcare. Standardized evaluations will build trust among users and professionals, facilitating broader adoption and improved mental health support through technology.

Fifteen-year-old Jordyne Lewis was stressed out. The high school sophomore from Harrisburg, North Carolina, was overwhelmed with schoolwork, never mind the uncertainty of living in a pandemic that has dragged on for two long years. Despite the challenges, she never turned to her school counselor or sought out a therapist. Instead, she shared her feelings with a robot. Lewis has struggled to cope with the changes and anxieties of pandemic life and for this extroverted teenager, loneliness and social isolation were among the biggest hardships.

While much of the focus around chatbots is in the customer service role, they also play a key part in helping people maintain their wellbeing, producing a positive outlook and engaging in other aspects of our health. During lockdown, the ability to talk to anyone, even a mental health chatbot about our troubles has proven to be a lifesaver. There is a lot of talk in the press and on social media that it is better to talk to someone about our problems than suffer in silence, especially during Mental Health Awareness Week 2020 and similar efforts. Mental health chatbots are a fast-growing segment in the bot market, with plenty arriving recently to help cater for those in lockdown during the Coronavirus who are unable to access their usual health systems. Not only are the bots innately helpful, but the stories that emerge from encounters help spread the word and encourage others to seek help from these digital AI mental health chatbots and solutions.

These patterns are wirelessly sent to rooms full of whirring, blinking supercomputers that translate them into words, meanings and actions. Behind this technology are decades of artificial intelligence research and millions of lines of computer code. We stand on the shoulders of giants when we say, Play Beethoven's Fifth, and our device responds with music to our ears: "da-da-da DUM," the opening of the composer's most famous symphony. Today, Stanford Medicine researchers are exploring ways to use intelligent listening technologies, natural language processing, machine learning and data mining to deliver better, more efficient health care. Here are a few of these projects.

Last December, Jesse Taylor was worried that the stress of his job and being a stay-at-home dad for his infant son was taking its toll. Taylor, 36, lives in Winnipeg and works as an operations manager for an online business. He felt overwhelmed by his responsibilities and distracted by the sleep deprivation that often comes with caring for a young child. And then his wife suggested that Taylor try one of Thriveport's mental health apps. "She suggested I give it a go to get out of those negative talk tracks I had gotten into from lack of sleep," he says.

Working 24 hours a day, 365 days a year across more than 130 countries, Woebot is undoubtedly a busy therapeutic chatbot. The good news is that Woebot recently secured $8 million to gain access to mental health care worldwide. The world's first mental health chatbot, Woebot was founded by Dr. Alison Darcey in 2017 for young adults in college and graduate school. Designed to use natural language processing, therapeutic expertise, excellent writing, Woebot comes with "occasional dorky joke". The therapeutic framework is said, "to create the experience of a therapeutic conversation for all of the people that use him."