From Pattern Recognizers to Personalized Companions: A Survey of Large Language Models in Mental Health
A survey traces mental-health LLMs from assessment tools to empathetic chat and stateful personalized companions.
This survey argues that LLM use in mental health has progressed through three phases: passive information and pattern-recognition tools, stateless empathetic conversationalists, and stateful personalized companion agents. It reviews supporting technologies, including profile, memory, reasoning, and planning architectures, plus datasets and benchmarks. The authors synthesize the literature and outline a roadmap for responsible, human-centered mental-health AI, with curated resources on GitHub.
- Frames three phases: assessment tools, empathetic chat, then personalized companions.
- Reviews profile, memory, reasoning, and planning in mental-health agents.
- Covers datasets, benchmarks, and a roadmap for responsible support AI.
From the original article
1 min read at huggingface.co
The rising global prevalence of mental health conditions, together with longstanding barriers in traditional healthcare, such as limited resources, high cost, stigma, and privacy concerns, has created an urgent need for accessible and scalable support.
By He Hu, Yucheng Zhou, Qianning Wang · huggingface.co
A short excerpt; the article and its images belong to the publisher. Summary, key facts and assessment above are AI-written from the article and can be wrong.