@bclavie: Very excited to finally share this one after sitting on it for far too long! It's very topical now. Blog post coming ve…

X AI KOLs Timeline Papers

Summary

Researchers extract indexable, BM25-ready sparse features from frozen dense retrievers using reconstruction-trained sparse autoencoders.

Very excited to finally share this one after sitting on it for far too long! It's very topical now. Blog post coming very soon :)
Original Article
View Cached Full Text

Cached at: 05/30/26, 08:46 PM

Very excited to finally share this one after sitting on it for far too long! It’s very topical now. Blog post coming very soon :)

Sumit (@_reachsumit): Latent Terms: Dense Retrievers Contain Trivially Extractable BM25-ready Zipfian Vocabularies

@bclavie et al. extract indexable, BM25-ready sparse features from frozen dense retrievers using reconstruction-trained Sparse Autoencoders.

📝

Similar Articles