OpenScholar: The open-source A.I. that’s outperforming GPT-4o in scientific research | VentureBeat

peter.suber's bookmarks 2025-01-08

Summary:

"At OpenScholar’s core is a retrieval-augmented language model that taps into a datastore of more than 45 million open-access academic papers....

When tasked with answering biomedical research questions, GPT-4o cited nonexistent papers in more than 90% of cases. OpenScholar, by contrast, remained firmly anchored in verifiable sources....

The OpenScholar team has released not only the code for the language model but also the entire retrieval pipeline, a specialized 8-billion-parameter model fine-tuned for scientific tasks, and a datastore of scientific papers....

Still, OpenScholar is not without limitations. Its datastore is restricted to open-access papers, leaving out paywalled research that dominates some fields...."

Link:

https://venturebeat.com/ai/openscholar-the-open-source-a-i-thats-outperforming-gpt-4o-in-scientific-research/

From feeds:

Open Access Tracking Project (OATP) » peter.suber's bookmarks

Tags:

oa.new oa.openscholar oa.ai oa.floss

Date tagged:

01/08/2025, 09:47

Date published:

01/08/2025, 04:47