{"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-ell-0-sparsification-for-inference","title":"Exploring $\\ell_0$ Sparsification for Inference-free Sparse Retrievers","arxiv_id":"2504.14839","date":"2025-04-21","proceeding":null,"authors":["Xinjie Shen","Zhichao Geng","Yang Yang"],"abstract":"With increasing demands for efficiency, information retrieval has developed a branch of sparse retrieval, further advancing towards inference-free retrieval where the documents are encoded during indexing time and there is no model-inference for queries. Existing sparse retrieval models rely on FLOPS regularization for sparsification, while this mechanism was originally designed for Siamese encoders, it is considered to be suboptimal in inference-free scenarios which is asymmetric. Previous attempts to adapt FLOPS for inference-free scenarios have been limited to rule-based methods, leaving the potential of sparsification approaches for inference-free retrieval models largely unexplored. In this paper, we explore $\\ell_0$ inspired sparsification manner for inference-free retrievers. Through comprehensive out-of-domain evaluation on the BEIR benchmark, our method achieves state-of-the-art performance among inference-free sparse retrieval models and is comparable to leading Siamese sparse retrieval models. Furthermore, we provide insights into the trade-off between retrieval effectiveness and computational efficiency, demonstrating practical value for real-world applications.","url_abs":"https://arxiv.org/abs/2504.14839v1","url_pdf":"https://arxiv.org/pdf/2504.14839v1.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-ell-0-sparsification-for-inference","repo_url":"https://github.com/zhichao-aws/opensearch-sparse-model-tuning-sample","is_official":1,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"Apache-2.0"}}],"tasks":[{"task_slug":"computational-efficiency","task_name":"Computational Efficiency"},{"task_slug":"information-retrieval","task_name":"Information Retrieval"},{"task_slug":"retrieval","task_name":"Retrieval"},{"task_slug":"zero-shot-on-beir-inference-free-model","task_name":"Zero Shot on BEIR (Inference Free Model)"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/zero-shot-on-beir-inference-free-model-on","task":"Zero Shot on BEIR (Inference Free Model)","dataset":"BEIR","model":"$\\ell_0$  Mask","rank_in_archive_order":1,"of":6,"metrics":{"NCDG@10":"50.43"},"uses_additional_data":false},{"leaderboard":"/sota/zero-shot-on-beir-inference-free-model-on","task":"Zero Shot on BEIR (Inference Free Model)","dataset":"BEIR","model":"$\\ell_0$  Mask-$\\ell_0$ Activation","rank_in_archive_order":2,"of":6,"metrics":{"NCDG@10":"50.28"},"uses_additional_data":false}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2504.14839","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2504.14839"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-24T18:15:14+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/zhichao-aws/opensearch-sparse-model-tuning-sample","reach":{"status":"ok","spdx":"Apache-2.0"}}],"summary":{"unverified":4},"by_repo_kind":{"official":{"samples":4,"ran":0,"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":"7832d9f14b77e01b","entry":"get_suffix","repo":"zhichao-aws/opensearch-sparse-model-tuning-sample","repo_kind":"official","path":"evaluate_beir.py","file_url":"https://github.com/zhichao-aws/opensearch-sparse-model-tuning-sample/blob/HEAD/evaluate_beir.py","link_basis":"harvester_set","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":"7832d9f14b77e01b"}},{"code_sha256_prefix":"3b7894704eb4b86c","entry":"load_beir_from_hf","repo":"zhichao-aws/opensearch-sparse-model-tuning-sample","repo_kind":"official","path":"evaluate_beir.py","file_url":"https://github.com/zhichao-aws/opensearch-sparse-model-tuning-sample/blob/HEAD/evaluate_beir.py","link_basis":"harvester_set","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":"3b7894704eb4b86c"}},{"code_sha256_prefix":"ad034320691a5d97","entry":"prepare_model_args","repo":"zhichao-aws/opensearch-sparse-model-tuning-sample","repo_kind":"official","path":"evaluate_beir.py","file_url":"https://github.com/zhichao-aws/opensearch-sparse-model-tuning-sample/blob/HEAD/evaluate_beir.py","link_basis":"harvester_set","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":"ad034320691a5d97"}},{"code_sha256_prefix":"6673ad87b0bcf7d2","entry":"transform_str","repo":"zhichao-aws/opensearch-sparse-model-tuning-sample","repo_kind":"official","path":"prepare_msmarco_hard_negatives.py","file_url":"https://github.com/zhichao-aws/opensearch-sparse-model-tuning-sample/blob/HEAD/prepare_msmarco_hard_negatives.py","link_basis":"harvester_set","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":"6673ad87b0bcf7d2"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}