OpenScholar: an open-source AI that masters literature reviews and cites correctly

TL;DR
An open-source AI called OpenScholar combines a language model with a 45-million-open-access-article database to perform literature reviews and cite sources directly, reducing hallucinations and allowing local deployment at a fraction of the cost of commercial deep-research tools; it’s powerful but may miss representative papers and is limited by its data coverage.
Topics:sciencetechnology#citations#literature-review#open-source#openscholar#retrieval-augmented#technology
- Open-source AI tool beats giant LLMs in literature reviews — and gets citations right Nature
- New chatbot ‘outperforms PhDs on literature reviews’, funds Nature study Times Higher Education
- AI model OpenScholar synthesizes scientific research and cites sources as accurately as human experts Phys.org
- OpenScholar AI Model Achieves Human-Level Accuracy in Synthesizing and Citing Scientific Research BIOENGINEER.ORG
Want the full story? Read the original reporting
Read on Nature