A Transposed Bock–Aitkin EM Algorithm for Item Response Models with Many Items and Few Subjects
Large language model benchmarks often contain many more items than evaluated systems. We develop a transposed Bock–Aitkin EM algorithm for 1PL and 2PL random-item models, including correlated difficulty and log discrimination. Capabilities are structural parameters; item effects are integrated over a normal population....
Preston Botter, Christopher Stewart
· 0 citations