Scientific papers are published faster than people can read and organize them. In the field of perovskite solar cells, the main database has been stuck in 2021, even though research is in full swing. Now PERLA comes to the rescue — an autonomous living database that keeps an eye on the flow of publications on its own.
PERLA uses large language models to extract complex device data from texts and then verifies it using physical rules. Extraction accuracy exceeds 90%, and unlike humans, the system does not suffer from inconsistencies in assessments. It is like a diligent librarian who never gets tired and never makes mistakes from fatigue.
Thanks to PERLA, static publications turn into a dynamic knowledge resource. Now researchers can rely on up-to-date data and move faster toward new discoveries. The database grows with science, not a day behind.
PERLA's data extraction accuracy is above 90%—comparable to an experienced expert, but without human errors and fatigue.