Pinned
My work at Elicit is out! We spent a lot of time trying to build the world's best systematic review evaluations.
I might be wrong, but I think this is the largest AI assisted SLR dataset in the *world* by 10x!!* We benchmark against ~994 papers versus ~100 for the next largest
How well does Elicit's semantic search work for systematic reviews?
Cochrane reviews are the gold standard for evidence synthesis in health and medicine. We sampled 888 reviews across 12 MeSH areas.
For each Cochrane systematic review, we ran Elicit using only the review title














