MétaCan
Menu
Back to cohort
Record W4406728115 · doi:10.1109/mnet.2025.3532857

PrismPrompt: Layering Prompt-Enhanced Cloud-Edge Collaborative Language Model Toward Healthcare

2025· article· en· W4406728115 on OpenAlexaff
Shuang Qiao, Hai‐Yang Xu, Chenhong Cao, Wei Gong, Si Chen, Jiangchuan Liu

Bibliographic record

VenueIEEE Network · 2025
Typearticle
Languageen
FieldComputer Science
TopicTopic Modeling
Canadian institutionsSimon Fraser University
Fundersnot available
KeywordsLayeringCloud computingComputer scienceEnhanced Data Rates for GSM EvolutionHealth careTelecommunicationsOperating system

Abstract

fetched live from OpenAlex

The rapid evolution of large language models (LLMs) has opened new avenues for enhancing healthcare delivery, particularly through cloud-edge collaborative frameworks. This paper introduces PrismPrompt, a novel system that leverages prompt-based engineering to optimize cloud-edge collaboration in medical applications. By integrating cloud-based LLMs with edge devices, PrismPrompt addresses the challenges of computational limitations and data privacy in healthcare environments. The system utilizes a hierarchical prompt strategy and an incremental expert decision-making process to enhance the retrieval and application of medical knowledge. Key innovations include a retriever module that accurately extracts and retrieves relevant information from cloud models and a decision maker that synthesizes expert opinions to ensure accurate and context-aware medical advice. Experimental results demonstrate that PrismPrompt outperforms existing models in terms of accuracy, highlighting its potential to improve real-time medical decision-making while preserving the computational feasibility on edge devices. This work provides a promising step towards the broader adoption of cloud-edge collaborative LLMs in healthcare, offering scalable and privacy-conscious solutions for modern medical challenges.

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 imitation

Not 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.

metaresearch head score (Codex)0.000
metaresearch head score (Gemma)0.000
Version: codex-gemma-dda1882f352aValidation status: machine_predicted_unvalidated
Candidate categoriesnone
Consensus categoriesnone
DomainCandidate signal: none · Consensus signal: none
Study designCandidate signal: Simulation or modeling · Consensus signal: Simulation or modeling
GenreCandidate signal: Methods · Consensus signal: none
Teacher disagreement score0.893
Threshold uncertainty score0.909

Codex and Gemma teacher scores by category

CategoryCodexGemma
Metaresearch0.0000.000
Meta-epidemiology (narrow)0.0000.000
Meta-epidemiology (broad)0.0000.000
Bibliometrics0.0000.001
Science and technology studies0.0000.000
Scholarly communication0.0000.000
Open science0.0010.000
Research integrity0.0000.000
Insufficient payload (model declined to judge)0.0000.000

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.

Opus teacher head0.022
GPT teacher head0.290
Teacher spread0.268 · how far apart the two teachers sit on this one work
Validation statusscore_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from it

Classification

machine, unvalidated

Machine predicted; a candidate call from one teacher head, not a consensus.

The models applied no category: nothing in the taxonomy fit this work.
Study designSimulation or modeling
Domainnot available
GenreMethods

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".

Quick stats

Citations7
Published2025
Admission routes1
Has abstractyes

Explore more

Same venueIEEE NetworkSame topicTopic ModelingFrench-language works237,207