English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

Large language models (LLMs), such as GPT-4, have demonstrated remarkablecapabilities across a wide range of tasks, including health applications. Inthis paper, we study how LLMs can be used to scale biomedical knowledgecuration. We find that while LLMs already possess decent competency instructuring biomedical text, by distillation into a task-specific student modelthrough self-supervised learning, substantial gains can be attained overout-of-box LLMs, with additional advantages such as cost, efficiency, andwhite-box model access.  We conduct a case study on adverse drug event (ADE) extraction, which is animportant area for improving care. On standard ADE extraction evaluation, aGPT-3.5 distilled PubMedBERT model attained comparable accuracy as supervisedstate-of-the-art models without using any labeled data. Despite being over1,000 times smaller, the distilled model outperformed its teacher GPT-3.5 byover 6 absolute points in F1 and GPT-4 by over 5 absolute points.  Ablation studies on distillation model choice (e.g., PubMedBERT vs BioGPT)and ADE extraction architecture shed light on best practice for biomedicalknowledge extraction. Similar gains were attained by distillation for otherstandard biomedical knowledge extraction tasks such as gene-diseaseassociations and protected health information, further illustrating the promiseof this approach.

Distilling Large Language Models for Biomedical Knowledge Extraction: A Case Study on Adverse Drug Events