Learned sparse retrieval
document search algorithm
Learned sparse retrieval (LSR) or sparse neural search is an approach to Information Retrieval which uses a sparse vector representation of queries and documents. It borrows techniques both from lexical bag-of-words and vector embedding algorithms, and is claimed to perform better than either alone. The best-known sparse neural search systems are SPLADE and its successor SPLADE v2. Others include DeepCT, uniCOIL, EPIC, DeepImpact, TILDE and TILDEv2, Sparta, SPLADE-max, and DistilSPLADE-max.
Multimodal Learned Sparse Retrieval. LSR approaches have also been extended to the vision-language domain, where they are applied to multimodal data, such as the combination of text and images. This expansion enables the retrieval of relevant content across different modalities, such as finding images based on text queries or vice versa.
Some implementations of SPLADE have similar latency to Okapi BM25 lexical search while giving as good results as state-of-the-art neural rankers on in-domain data.
The Official SPLADE model weights and training code is released under a Creative Commons NonCommercial license. But there are other independent implementations of SPLADE++ (a variant of SPLADE models) that are released under permissive licenses.
This brief starts where responsible research should: with the source description of “Learned sparse retrieval” as document search algorithm. Everything that follows is an evidence route, not borrowed authority.
Why this record matters
The subject matters to the general reference register because the source frames it as document search algorithm. Its deeper value depends on whether names, dates, institutions and citations support that framing.
Vocabulary and entity names are the principal evidence signals here, because they determine the precision of every later search. The source revision retrieved here is dated Jan 14, 2026. The linked authority identifier is Q122363545. None of the 0 selected statements returned an explicit reference.
The absence of detail may reflect summary conventions rather than a lack of surviving documentation. The lead is largely declarative, so disagreement and counter-evidence require a deliberate search beyond the opening account. Authority statements aid reconciliation but still require their own references, qualifiers and ranks to be checked.
How to read it
Use the entry as an orientation point, then follow its citations and revision history. Names, dates and institutional relationships should be checked against the original record.
- Subject orientation
- Search vocabulary
- Locating named sources
The closest primary source, responsible institution and strongest cited specialist reference.
Three-step research path
- Establish the record: confirm the title “Learned sparse retrieval”, its source revision and the description used here.
- Expand the search: follow Learned sparse retrieval primary sources, Learned sparse retrieval archive and Learned research across catalogues and specialist indexes.
- Test the account: compare the strongest cited source with the responsible institution’s current record and note any disagreement.
Questions for further research
- Which source most directly establishes the central claim about “Learned sparse retrieval”?
- Which institution is responsible for the underlying evidence?
- Which cited source is closest to the event, object or claim?
Search terms from this dossier
This entry incorporates text from “Learned sparse retrieval” on English Wikipedia. Contributors are listed in the page history. Text is available under the Creative Commons Attribution-ShareAlike 4.0 License. Selected authority identifiers and statements are retrieved from Wikidata under CC0; their references and qualifiers remain part of the verification path.