FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W4385650777> ?p ?o ?g. }

• W4385650777 abstract "<sec> <title>BACKGROUND</title> Generative large language models (LLMs) have the potential to revolutionize medical education by generating tailored learning materials, enhancing teaching efficiency, and improving learner engagement. However, the application of LLMs in healthcare settings, particularly for augmenting small datasets in text classification tasks, remains underexplored, particularly for cost- and privacy-conscious applications that do not permit the use of third-party services such as OpenAI’s ChatGPT. </sec> <sec> <title>OBJECTIVE</title> This paper explores the use of open-source LLMs, such as Large Language Model Meta AI (LLaMA) and Alpaca models, for data augmentation in a specific text classification task related to hospital staff surveys. </sec> <sec> <title>METHODS</title> The surveys were designed to elicit narratives of everyday adaptation by frontline radiology staff during the initial phase of the COVID-19 pandemic. The study evaluates the effectiveness of various LLMs, temperature settings, and downstream classifiers in improving classifier performance. </sec> <sec> <title>RESULTS</title> The overall best-performing combination of LLM, temperature, classifier, and number of augments is LLaMA 7B at temperature 0.7 using Robustly Optimized BERT Pretraining Approach (RoBERTa) with 100 augments, with an average the Area Under the Receiver Operating Characteristic curve (AUC) of [0.87] ±[0.02: 1 standard deviation]. The results demonstrate that open-source LLMs can enhance text classifiers' performance for small datasets in healthcare contexts, providing promising pathways for improving medical education processes and patient care practices. </sec> <sec> <title>CONCLUSIONS</title> The study demonstrates the value of data augmentation with open-source LLMs, highlights the importance of privacy and ethical considerations when using LLMs, and suggests future directions for research in this field. </sec>" @default.
• W4385650777 created "2023-08-09" @default.
• W4385650777 creator A5022226123 @default.
• W4385650777 creator A5043963254 @default.
• W4385650777 creator A5086799378 @default.
• W4385650777 creator A5088496314 @default.
• W4385650777 creator A5092611052 @default.
• W4385650777 date "2023-07-31" @default.
• W4385650777 modified "2023-09-25" @default.
• W4385650777 title "Leveraging Open-Source Large Language Models for Data Augmentation to Improve Text Classification in Surveys of Medical Staff (Preprint)" @default.
• W4385650777 cites W2969241973 @default.
• W4385650777 cites W3120697974 @default.
• W4385650777 cites W3133805210 @default.
• W4385650777 cites W3134399782 @default.
• W4385650777 cites W3186552329 @default.
• W4385650777 cites W3198433729 @default.
• W4385650777 cites W4242504853 @default.
• W4385650777 cites W4280602135 @default.
• W4385650777 cites W4282916733 @default.
• W4385650777 cites W4285310604 @default.
• W4385650777 cites W4287891041 @default.
• W4385650777 cites W4294015801 @default.
• W4385650777 cites W4308842159 @default.
• W4385650777 cites W4312209916 @default.
• W4385650777 cites W4313460860 @default.
• W4385650777 cites W4318219754 @default.
• W4385650777 cites W4318925155 @default.
• W4385650777 cites W4319301505 @default.
• W4385650777 cites W4319662928 @default.
• W4385650777 cites W4319663047 @default.
• W4385650777 cites W4320895630 @default.
• W4385650777 cites W4321435202 @default.
• W4385650777 cites W4323315429 @default.
• W4385650777 cites W4323350039 @default.
• W4385650777 cites W4324130227 @default.
• W4385650777 cites W4327915219 @default.
• W4385650777 cites W4360980513 @default.
• W4385650777 cites W4363645798 @default.
• W4385650777 doi "https://doi.org/10.2196/preprints.51433" @default.
• W4385650777 hasPublicationYear "2023" @default.
• W4385650777 type Work @default.
• W4385650777 citedByCount "0" @default.
• W4385650777 crossrefType "posted-content" @default.
• W4385650777 hasAuthorship W4385650777A5022226123 @default.
• W4385650777 hasAuthorship W4385650777A5043963254 @default.
• W4385650777 hasAuthorship W4385650777A5086799378 @default.
• W4385650777 hasAuthorship W4385650777A5088496314 @default.
• W4385650777 hasAuthorship W4385650777A5092611052 @default.
• W4385650777 hasConcept C119857082 @default.
• W4385650777 hasConcept C154945302 @default.
• W4385650777 hasConcept C160735492 @default.
• W4385650777 hasConcept C17744445 @default.
• W4385650777 hasConcept C199360897 @default.
• W4385650777 hasConcept C199539241 @default.
• W4385650777 hasConcept C204321447 @default.
• W4385650777 hasConcept C2522767166 @default.
• W4385650777 hasConcept C2777904410 @default.
• W4385650777 hasConcept C3018397939 @default.
• W4385650777 hasConcept C41008148 @default.
• W4385650777 hasConcept C95623464 @default.
• W4385650777 hasConceptScore W4385650777C119857082 @default.
• W4385650777 hasConceptScore W4385650777C154945302 @default.
• W4385650777 hasConceptScore W4385650777C160735492 @default.
• W4385650777 hasConceptScore W4385650777C17744445 @default.
• W4385650777 hasConceptScore W4385650777C199360897 @default.
• W4385650777 hasConceptScore W4385650777C199539241 @default.
• W4385650777 hasConceptScore W4385650777C204321447 @default.
• W4385650777 hasConceptScore W4385650777C2522767166 @default.
• W4385650777 hasConceptScore W4385650777C2777904410 @default.
• W4385650777 hasConceptScore W4385650777C3018397939 @default.
• W4385650777 hasConceptScore W4385650777C41008148 @default.
• W4385650777 hasConceptScore W4385650777C95623464 @default.
• W4385650777 hasLocation W43856507771 @default.
• W4385650777 hasOpenAccess W4385650777 @default.
• W4385650777 hasPrimaryLocation W43856507771 @default.
• W4385650777 hasRelatedWork W2556319748 @default.
• W4385650777 hasRelatedWork W2961085424 @default.
• W4385650777 hasRelatedWork W3046775127 @default.
• W4385650777 hasRelatedWork W3170094116 @default.
• W4385650777 hasRelatedWork W4205958290 @default.
• W4385650777 hasRelatedWork W4285260836 @default.
• W4385650777 hasRelatedWork W4286629047 @default.
• W4385650777 hasRelatedWork W4306321456 @default.
• W4385650777 hasRelatedWork W4306674287 @default.
• W4385650777 hasRelatedWork W4224009465 @default.
• W4385650777 isParatext "false" @default.
• W4385650777 isRetracted "false" @default.
• W4385650777 workType "article" @default.