• Carnegie Mellon University School of Computer Science The Breakdown OpenScholar is an AI model developed to help scientists keep up with new discoveries. • The model was trained on 45 million scientific papers and can incorporate new ones. • Scientists preferred OpenScholar answers to human answers 51% of the time. • *** A team of researchers led by an incoming Carnegie Mellon University professor has built an open-source artificial intelligence model designed specifically to synthesize current scientific research. • Akari Asai, who will join theLanguage Technologies Institutein CMU’s School of Computer Science as an assistant professor this fall, said the new tool,OpenScholar, will help researchers stay on top of the latest scientific breakthroughs. • “Scientists see so many papers coming out every day that it’s impossible to keep up,” said Asai, the lead author on the paper describing OpenScholar.
Article Summaries:
- Researchers led by incoming Carnegie Mellon professor Akari Asai have released OpenScholar, an open‑source AI model that synthesizes scientific literature. Built at the Allen Institute for AI and trained on 45 million research papers, the system uses retrieval‑augmented generation to ground responses in current studies and to cite sources accurately. A new benchmark, ScholarQABench, contains 3,000 expert‑written queries across computer science, physics, biomedicine, and neuroscience, and shows OpenScholar outperforming general‑purpose models such as GPT‑4o and Meta’s offerings. The tool aims to help scientists keep up with the rapid pace of publications while reducing hallucinations common in existing AI systems.
Sources: