ReviewFact
ReviewFact: Factual Errors in Peer-Review Comments ReviewFact is the benchmark of the paper PremiseCheck: Efficient Fact-Checking of Human and AI Peer Reviews.
How to run
$ npm i -g lettokenburn-cli$ ltb bench info reviewfact
External harness. No Harbor adapter has been generated for this benchmark yet. `ltb bench info` prints the known links.
Runs happen on your machine with your own subscription; only the score summary is pushed. CLI docs
Scores
4 sourced entriesEvery number links to where it was published. Low-confidence rows are muted and need per-cell verification.
Reproduced by the community
All runsAbout
ReviewFact: Factual Errors in Peer-Review Comments
ReviewFact is the benchmark of the paper PremiseCheck: Efficient Fact-Checking of Human and AI Peer Reviews. Dingjie Song1, Zhiling Yan1, Ziqian Zhang1, Yuxuan Zhang2,3, Lichao Sun1 1Lehigh University, 2University of British Columbia, 3Vector Institute
(a) The task on a real ReviewFact comment that claims a baseline is missing although the paper reports it. (b) ReviewFact labels come from the expert annotations of three…