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

Objective To develop soft prompt-based learning algorithms for large languagemodels (LLMs), examine the shape of prompts, prompt-tuning usingfrozen/unfrozen LLMs, transfer learning, and few-shot learning abilities.Methods We developed a soft prompt-based LLM model and compared 4 trainingstrategies including (1) fine-tuning without prompts; (2) hard-prompt withunfrozen LLMs; (3) soft-prompt with unfrozen LLMs; and (4) soft-prompt withfrozen LLMs. We evaluated 7 pretrained LLMs using the 4 training strategies forclinical concept and relation extraction on two benchmark datasets. Weevaluated the transfer learning ability of the prompt-based learning algorithmsin a cross-institution setting. We also assessed the few-shot learning ability.Results and Conclusion When LLMs are unfrozen, GatorTron-3.9B with softprompting achieves the best strict F1-scores of 0.9118 and 0.8604 for conceptextraction, outperforming the traditional fine-tuning and hard prompt-basedmodels by 0.6~3.1% and 1.2~2.9%, respectively; GatorTron-345M with softprompting achieves the best F1-scores of 0.8332 and 0.7488 for end-to-endrelation extraction, outperforming the other two models by 0.2~2% and0.6~11.7%, respectively. When LLMs are frozen, small (i.e., 345 millionparameters) LLMs have a big gap to be competitive with unfrozen models; scalingLLMs up to billions of parameters makes frozen LLMs competitive with unfrozenLLMs. For cross-institute evaluation, soft prompting with a frozenGatorTron-8.9B model achieved the best performance. This study demonstratesthat (1) machines can learn soft prompts better than humans, (2) frozen LLMshave better few-shot learning ability and transfer learning ability tofacilitate muti-institution applications, and (3) frozen LLMs require largemodels.

Model Tuning or Prompt Tuning? A Study of Large Language Models for Clinical Concept and Relation Extraction