CalmSphere: An AI for Mental Health
Bibliographic record
Abstract
Mental health is a global issue but access to professionals is limited due to cost, stigma and lack of skilled therapists. Existing AI powered mental health chatbots try to bridge the gap but suffer from many limitations like no empathy, rule based responses and inability to personalize conversations. Through a critical analysis of existing AI therapy tools, we identify key gaps in empathy and efficiency, motivating CalmSphere’s development Our research shows that most existing LLM based solutions rely on prompt engineering rather than fine tuning for therapeutic applications. This analysis is the foundation of our research and guides the development of CalmSphere.This paper introduces CalmSphere, an AI driven virtual therapist to enhance mental health support using a fine tuned Micro-LLM based on LLaMA 2-7B. Unlike traditional AI therapy models, CalmSphere uses memory driven personalization, active listening and emotion aware responses to have a more empathetic and human like conversation. The model is fine tuned using Quantized Low-Rank Adaptation (QLoRA) for efficient training and can be deployed on resource constrained systems with high performance.Also this paper presents a detailed evaluation of CalmSphere’s performance in generating contextually relevant, engaging and supportive conversations.
Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.
How this classification was reachedexpand
Full frame machine prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. The Gemma side is a direct model label for every work in the frame, read from the title-only record. The Codex side is a classifier learned from the 10,348 direct Codex labels and calibrated to design-weighted sample rates; fields without enough sample support carry no Codex call. Candidate is the union of the two sides; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels.
Distilled classifier scores by category (both heads)
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.001 | 0.004 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.000 |
| Bibliometrics | 0.000 | 0.000 |
| Science and technology studies | 0.001 | 0.000 |
| Scholarly communication | 0.001 | 0.001 |
| Open science | 0.001 | 0.003 |
| Research integrity | 0.001 | 0.001 |
| Insufficient payload (model declined to judge) | 0.035 | 0.006 |
Machine scores (provisional)
The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.
Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.
score_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from itClassification
machine, unvalidatedMachine predicted; a candidate call from one source (direct Gemma or distilled Codex), not a consensus.
How this classification was reached, model by model and score by score, is at the end of the page under "How this classification was reached".