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

Molecule discovery serves as a cornerstone in numerous scientific domains,fueling the development of new materials and innovative drug designs. Recentdevelopments of in-silico molecule discovery have highlighted the promisingresults of cross-modal techniques, which bridge molecular structures with theirdescriptive annotations. However, these cross-modal methods frequentlyencounter the issue of data scarcity, hampering their performance andapplication. In this paper, we address the low-resource challenge by utilizingartificially-real data generated by Large Language Models (LLMs). We firstintroduce a retrieval-based prompting strategy to construct high-quality pseudodata, then explore the optimal method to effectively leverage this pseudo data.Experiments show that using pseudo data for domain adaptation outperforms allexisting methods, while also requiring a smaller model scale, reduced data sizeand lower training cost, highlighting its efficiency. Furthermore, our methodshows a sustained improvement as the volume of pseudo data increases, revealingthe great potential of pseudo data in advancing low-resource cross-modalmolecule discovery. Our code and data are available athttps://github.com/SCIR-HI/ArtificiallyR2R.

From Artificially Real to Real: Leveraging Pseudo Data from Large Language Models for Low-Resource Molecule Discovery