Can a Frozen Pretrained Language Model be used for Zero-shot Neural Retrieval on Entity-centric Questions?

Open paper
Benchmark Model Rank Results
passage-retrieval-on-entityquestionsContriever–Recall@20: 0.647
passage-retrieval-on-entityquestionsZero-NeR–Recall@20: 0.671

Rank counts only results with a code link.