**TILDEv2** is a [BERT](https://paperswithcode.com/method/bert)-based re-ranking method that stems from [TILDE](https://dl.acm.org/doi/abs/10.1145/3404835.3462922) but that addresses its limitations. It relies on contextualized exact term matching with expanded passages. This requires to only store in the index the score of tokens that appear in the expanded passages (rather than all the vocabulary), thus producing indexes that are 99% smaller than those of the original. ![[Pasted image 20240905163628.png]] [[Reranking Methods]]