{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/exploring-the-representation-power-of-splade","title":"Exploring the Representation Power of SPLADE Models","arxiv_id":"2306.16680","date":"2023-06-29","proceeding":null,"authors":["Joel Mackenzie","Shengyao Zhuang","Guido Zuccon"],"abstract":"The SPLADE (SParse Lexical AnD Expansion) model is a highly effective approach to learned sparse retrieval, where documents are represented by term impact scores derived from large language models. During training, SPLADE applies regularization to ensure postings lists are kept sparse -- with the aim of mimicking the properties of natural term distributions -- allowing efficient and effective lexical matching and ranking. However, we hypothesize that SPLADE may encode additional signals into common postings lists to further improve effectiveness. To explore this idea, we perform a number of empirical analyses where we re-train SPLADE with different, controlled vocabularies and measure how effective it is at ranking passages. Our findings suggest that SPLADE can effectively encode useful ranking signals in documents even when the vocabulary is constrained to terms that are not traditionally useful for ranking, such as stopwords or even random words.","url_abs":"https://arxiv.org/abs/2306.16680v1","url_pdf":"https://arxiv.org/pdf/2306.16680v1.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"exploring-the-representation-power-of-splade","repo_url":"https://github.com/ielab/understanding-splade","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"jax","reach":{"status":"ok","spdx":"Apache-2.0"}}],"tasks":[{"task_slug":"retrieval","task_name":"Retrieval"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/2306.16680","atlas_url":"https://app.syntology.ai/?focus=2306.16680","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2306.16680"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-25T09:33:49+00:00","read_at_is":"when the build read Syntology's graph, not when any sample ran","claim":"Per-sample execution status on synthesized fixtures; not a correctness claim about the paper. Samples come from repositories linked to the paper, official or community; repo_kind says which.","repos":[{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/ielab/understanding-splade","reach":{"status":"ok","spdx":"Apache-2.0"}}],"summary":{"ran":4,"unverified":1},"by_repo_kind":{"official":{"samples":5,"ran":4,"repositories":1}},"repo_kind_vocabulary":{"official":"The archive marks this repository official for the paper","named_in_paper":"The archive records that the paper mentions this repository; it is not marked official","listed":"In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper","found_in_text":"Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted","community":"Not in the archive's code links for this paper; a community repository Syntology harvested"},"n_pointer_only_for_licence":0,"samples":[{"code_sha256_prefix":"9adb9c459cc4c8f0","entry":"combine_faiss_results","repo":"ielab/understanding-splade","repo_kind":"official","path":"tevatron/src/tevatron/faiss_retriever/reducer.py","file_url":"https://github.com/ielab/understanding-splade/blob/HEAD/tevatron/src/tevatron/faiss_retriever/reducer.py","link_basis":"plan_row","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"9adb9c459cc4c8f0"}},{"code_sha256_prefix":"fd973ee45608bfd5","entry":"get_dense_rep","repo":"ielab/understanding-splade","repo_kind":"official","path":"tevatron/src/tevatron/trainer.py","file_url":"https://github.com/ielab/understanding-splade/blob/HEAD/tevatron/src/tevatron/trainer.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"fd973ee45608bfd5"}},{"code_sha256_prefix":"01c4c73be2b9b863","entry":"search_queries","repo":"ielab/understanding-splade","repo_kind":"official","path":"tevatron/src/tevatron/faiss_retriever/__main__.py","file_url":"https://github.com/ielab/understanding-splade/blob/HEAD/tevatron/src/tevatron/faiss_retriever/__main__.py","link_basis":"plan_row","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"01c4c73be2b9b863"}},{"code_sha256_prefix":"a68ca4e05b568068","entry":"split_dense_inputs","repo":"ielab/understanding-splade","repo_kind":"official","path":"tevatron/src/tevatron/trainer.py","file_url":"https://github.com/ielab/understanding-splade/blob/HEAD/tevatron/src/tevatron/trainer.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"a68ca4e05b568068"}},{"code_sha256_prefix":"d5944ba894d22f55","entry":"pickle_load","repo":"ielab/understanding-splade","repo_kind":"official","path":"tevatron/src/tevatron/faiss_retriever/__main__.py","file_url":"https://github.com/ielab/understanding-splade/blob/HEAD/tevatron/src/tevatron/faiss_retriever/__main__.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"d5944ba894d22f55"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}