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

The patient-centered medical dialogue systems strive to offer diagnosticinterpretation services to users who are less knowledgeable about medicalknowledge, through emphasizing the importance of providing responses specificto the patients. It is difficult for the large language models (LLMs) toguarantee the specificity of responses in spite of its promising performanceeven in some tasks in medical field. Inspired by in-context learning, wepropose PlugMed, a Plug-and-Play Medical Dialogue System, for addressing thischallenge. PlugMed is equipped with two modules, the prompt generation (PG)module and the response ranking (RR) module, to enhances LLMs' dialoguestrategies for improving the specificity of the dialogue. The PG module isdesigned to stimulate the imitative ability of LLMs by providing them with realdialogues from similar patients as prompts. The RR module incorporatesfine-tuned small model as response filter to enable the selection ofappropriate responses generated by LLMs. Furthermore, we introduce a newevaluation method based on matching both user's intent and high-frequencymedical term to effectively assess the specificity of the responses. We conductexperimental evaluations on three medical dialogue datasets, and the results,including both automatic and human evaluation, demonstrate the effectiveness ofour approach.

PlugMed: Improving Specificity in Patient-Centered Medical Dialogue Generation using In-Context Learning