Bibliographic record
Abstract
As sleep health becomes increasingly central to personal well-being, individuals are turning to digital tools for education, tracking, and behavior change support. Large language models like ChatGPT and Gemini have recently emerged as promising components of these tools, capable of generating personalized, conversational, and context-aware sleep guidance. This scoping survey synthesizes findings from 21 papers that explore the use of large language models in nonclinical, everyday user-focused applications for sleep health. We organize the literature into 4 core use cases: educational question answering, condition-specific support (eg, obstructive sleep apnea), personalized recommendations and coaching, and cognitive behavioral therapy-based self-help systems. We analyze the diverse data sources involved-including wearable sensor data, self-reported metrics, and synthetic benchmarks-as well as model architectures, fine-tuning techniques, and personalization strategies. Finally, we examine evaluation frameworks ranging from expert review to pilot user studies and LLM-based scoring. The review highlights current capabilities, methodological challenges, and open opportunities for advancing trustworthy, personalized sleep support using generative artificial intelligence, while emphasizing that much of the evidence remains preliminary, often short-term, expert-rated, or proxy-based, which limits external validity and generalizability.
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 | 0.010 | 0.036 |
| Meta-epidemiology (narrow) | 0.002 | 0.001 |
| Meta-epidemiology (broad) | 0.004 | 0.004 |
| Bibliometrics | 0.008 | 0.008 |
| Science and technology studies | 0.001 | 0.001 |
| Scholarly communication | 0.003 | 0.003 |
| Open science | 0.002 | 0.002 |
| Research integrity | 0.002 | 0.002 |
| Insufficient payload (model declined to judge) | 0.006 | 0.001 |
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".