LLM-Therapist: A RAG-Based Multimodal Behavioral Therapist as Healthcare Assistant
Bibliographic record
Abstract
Systems and services based on Large Language Models (LLM) are trending in the applied field of Artificial Intelligence (AI). The emergence of GPTs and subsequent improvements such as, unsupervised pre-training and transformer architecture have lead to its ability to generate human-quality text and understand context effectively. This has opened huge opportunity in healthcare domain to use AI-based assistant systems that can offer tailored recommendations and guidance for patients in numerous scenarios by considering multimodal data. This paper proposes LLM-Therapist as a multimodal personalized health care assistant for various types of patients. The proposed system uses Retrieval Augmented Generation (RAG) technique to improve the quality, accuracy, and relevance of generated response, which is specially important in providing healthcare assistance. We conducted experiments with LLM-therapist by extracting knowledge from domain-specific resources in mental health and patient’s health data. Our experiments showed better efficiency and performance in providing personalized assistance.
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 distilled prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. Learned from the 10,348 direct Codex labels and 10,348 direct Gemma labels. Candidate is the union of thresholded teacher heads; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels or direct frontier model labels.
Codex and Gemma teacher scores by category
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.000 | 0.000 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.000 |
| Bibliometrics | 0.000 | 0.000 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.000 | 0.000 |
| Open science | 0.000 | 0.000 |
| Research integrity | 0.000 | 0.001 |
| Insufficient payload (model declined to judge) | 0.021 | 0.003 |
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; both teacher heads agree on what is shown here.
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".