Recent advances in large language models have enabled the development of viable generative retrieval systems. Instead of a traditional document ranking, generative retrieval systems often directly return a grounded generated text as a response to a query.

Cross-encoders are effective passage re-rankers. But when re-ranking multiple passages at once, existing cross-encoders inefficiently optimize the output ranking over several input permutations, as their passage interactions are not permutation-invariant. Moreover, their high memory footprint constrains the number of passages during listwise training.