Can AI review the scientific literature — and figure out what it all means?

AI-powered science search engines can already help people to produce narrative literature reviews by finding, sorting and summarizing publications.

But they can’t yet produce a high-quality review by themselves.

Large language models generate text by training on enormous amounts of writing, but most commercial AI firms do not reveal what data the models were trained on.

AI science search engines cannot produce an accurate literature review autonomously.

They can only search open-access papers and abstracts, rather than the full text of articles.

PaperQA2 , FutureHouse ’s open-source, prototype AI system, is backed by former Google chief executive Eric Schmidt .

Systematic-review aficionados worry that AI tools are at risk of failing to meet two essential criteria of the studies: transparency and reproducibility.

Elicit is one company that says its tool helps researchers with systematic reviews, not just narrative ones.

The firm does not offer systematic reviews at the push of a button, but its system does automate some of the steps.