Our verdict
Being tested. An editor is using Semantic Scholar hands-on; the verdict and score appear here once they sign it off.
What it does
Semantic Scholar is a free search engine for academic papers from Ai2, a non-profit AI research institute. It covers science and many other fields, and many papers have a one-sentence AI summary, so you can see quickly what each one found.
It also tracks citations and recommends related papers, and for many papers it offers Semantic Reader, which shows details of each paper cited as you read.
Why use it
- It is free, with no paid plan to upgrade to.
- One-sentence summaries help you sort through search results quickly.
- Recommendations point you to related and newer papers.
- It is run by a non-profit research institute.
How it works
- Go to semanticscholar.org and search for a topic, paper or author.
- Skim the one-line summaries to pick the papers that matter.
- Open a paper to see its abstract, citations and related work.
- Create a free account to save papers to your library.
How hard is it to use?
Intermediate Some set-up, or a little practice, to get good results.
Searching is easy, but reading and judging academic papers takes some background, which is why we rate it Intermediate.
What it costs
Free. Free. It is run by Ai2, a non-profit, and has no paid plan.
Prices change often, so check Semantic Scholar’s own site before you pay.
Watch out for
- Short AI summaries can leave out important caveats, so read the paper before you cite it.
- Some papers it lists sit behind publishers’ paywalls.
Your data
You can search without an account. If you create one, check Ai2’s privacy policy for what it keeps about your library and searches.
We haven’t confirmed that Semantic Scholar can keep your data in the UK, so check where it keeps your data before you share anything private or about other people.