{"id":"https://openalex.org/W7167920050","doi":"https://doi.org/10.1145/3805712.3809625","title":"Adaptive Sparsity Optimization with Learnable Soft Top- <i>K</i> and Per-Term Thresholding for Efficient Retrieval","display_name":"Adaptive Sparsity Optimization with Learnable Soft Top- <i>K</i> and Per-Term Thresholding for Efficient Retrieval","publication_year":2026,"publication_date":"2026-07-10","ids":{"openalex":"https://openalex.org/W7167920050","doi":"https://doi.org/10.1145/3805712.3809625"},"language":null,"primary_location":{"id":"doi:10.1145/3805712.3809625","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3805712.3809625","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 49th International ACM SIGIR Conference on Research and Development in Information Retrieval","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.1145/3805712.3809625","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5101939239","display_name":"Wentai Xie","orcid":null},"institutions":[{"id":"https://openalex.org/I154570441","display_name":"University of California, Santa Barbara","ror":"https://ror.org/02t274463","country_code":"US","type":"education","lineage":["https://openalex.org/I154570441"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Wentai Xie","raw_affiliation_strings":["University of California, Santa Barbara, Santa Barbara, CA, USA"],"raw_orcid":"https://orcid.org/0009-0007-7870-3100","affiliations":[{"raw_affiliation_string":"University of California, Santa Barbara, Santa Barbara, CA, USA","institution_ids":["https://openalex.org/I154570441"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5018045958","display_name":"Parker Carlson","orcid":"https://orcid.org/0000-0003-1856-5088"},"institutions":[{"id":"https://openalex.org/I154570441","display_name":"University of California, Santa Barbara","ror":"https://ror.org/02t274463","country_code":"US","type":"education","lineage":["https://openalex.org/I154570441"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Parker Carlson","raw_affiliation_strings":["University of California, Santa Barbara, Santa Barbara, CA, USA"],"raw_orcid":"https://orcid.org/0000-0003-1856-5088","affiliations":[{"raw_affiliation_string":"University of California, Santa Barbara, Santa Barbara, CA, USA","institution_ids":["https://openalex.org/I154570441"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5037790148","display_name":"Shanxiu He","orcid":"https://orcid.org/0009-0008-8581-6733"},"institutions":[{"id":"https://openalex.org/I154570441","display_name":"University of California, Santa Barbara","ror":"https://ror.org/02t274463","country_code":"US","type":"education","lineage":["https://openalex.org/I154570441"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Shanxiu He","raw_affiliation_strings":["University of California, Santa Barbara, Santa Barbara, CA, USA"],"raw_orcid":"https://orcid.org/0009-0008-8581-6733","affiliations":[{"raw_affiliation_string":"University of California, Santa Barbara, Santa Barbara, CA, USA","institution_ids":["https://openalex.org/I154570441"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5060730782","display_name":"Tao Yang","orcid":"https://orcid.org/0000-0003-1902-3387"},"institutions":[{"id":"https://openalex.org/I154570441","display_name":"University of California, Santa Barbara","ror":"https://ror.org/02t274463","country_code":"US","type":"education","lineage":["https://openalex.org/I154570441"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Tao Yang","raw_affiliation_strings":["University of California, Santa Barbara, Santa Barbara, CA, USA"],"raw_orcid":"https://orcid.org/0000-0003-1902-3387","affiliations":[{"raw_affiliation_string":"University of California, Santa Barbara, Santa Barbara, CA, USA","institution_ids":["https://openalex.org/I154570441"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I154570441"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.96804538,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"2072","last_page":"2083"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10286","display_name":"Information Retrieval and Search Behavior","score":0.6586999893188477,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T10286","display_name":"Information Retrieval and Search Behavior","score":0.6586999893188477,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.062199998646974564,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.027300000190734863,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/scheme","display_name":"Scheme (mathematics)","score":0.5088000297546387},{"id":"https://openalex.org/keywords/thresholding","display_name":"Thresholding","score":0.5055000185966492},{"id":"https://openalex.org/keywords/regularization","display_name":"Regularization (linguistics)","score":0.503000020980835},{"id":"https://openalex.org/keywords/relevance","display_name":"Relevance (law)","score":0.44339999556541443},{"id":"https://openalex.org/keywords/term","display_name":"Term (time)","score":0.39910000562667847},{"id":"https://openalex.org/keywords/minification","display_name":"Minification","score":0.390500009059906},{"id":"https://openalex.org/keywords/latency","display_name":"Latency (audio)","score":0.3646000027656555}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7749000191688538},{"id":"https://openalex.org/C77618280","wikidata":"https://www.wikidata.org/wiki/Q1155772","display_name":"Scheme (mathematics)","level":2,"score":0.5088000297546387},{"id":"https://openalex.org/C191178318","wikidata":"https://www.wikidata.org/wiki/Q2256906","display_name":"Thresholding","level":3,"score":0.5055000185966492},{"id":"https://openalex.org/C2776135515","wikidata":"https://www.wikidata.org/wiki/Q17143721","display_name":"Regularization (linguistics)","level":2,"score":0.503000020980835},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4796000123023987},{"id":"https://openalex.org/C158154518","wikidata":"https://www.wikidata.org/wiki/Q7310970","display_name":"Relevance (law)","level":2,"score":0.44339999556541443},{"id":"https://openalex.org/C61797465","wikidata":"https://www.wikidata.org/wiki/Q1188986","display_name":"Term (time)","level":2,"score":0.39910000562667847},{"id":"https://openalex.org/C147764199","wikidata":"https://www.wikidata.org/wiki/Q6865248","display_name":"Minification","level":2,"score":0.390500009059906},{"id":"https://openalex.org/C82876162","wikidata":"https://www.wikidata.org/wiki/Q17096504","display_name":"Latency (audio)","level":2,"score":0.3646000027656555},{"id":"https://openalex.org/C99016210","wikidata":"https://www.wikidata.org/wiki/Q5488129","display_name":"Query expansion","level":2,"score":0.3328999876976013},{"id":"https://openalex.org/C3826847","wikidata":"https://www.wikidata.org/wiki/Q188768","display_name":"FLOPS","level":2,"score":0.3328000009059906},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.305400013923645},{"id":"https://openalex.org/C2779532271","wikidata":"https://www.wikidata.org/wiki/Q445558","display_name":"Relevance feedback","level":4,"score":0.29440000653266907},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.2904999852180481},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.28209999203681946},{"id":"https://openalex.org/C161156560","wikidata":"https://www.wikidata.org/wiki/Q1638872","display_name":"Document retrieval","level":2,"score":0.2768000066280365},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.2662000060081482},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.2540999948978424},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.25040000677108765}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3805712.3809625","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3805712.3809625","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 49th International ACM SIGIR Conference on Research and Development in Information Retrieval","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3805712.3809625","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3805712.3809625","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 49th International ACM SIGIR Conference on Research and Development in Information Retrieval","raw_type":"proceedings-article"},"sustainable_development_goals":[{"score":0.5260342955589294,"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":19,"referenced_works":["https://openalex.org/W2006997130","https://openalex.org/W2025345306","https://openalex.org/W2135290016","https://openalex.org/W2740817677","https://openalex.org/W2897754576","https://openalex.org/W3154280800","https://openalex.org/W3154755316","https://openalex.org/W4284663260","https://openalex.org/W4284664419","https://openalex.org/W4381573351","https://openalex.org/W4384643607","https://openalex.org/W4384891026","https://openalex.org/W4385688528","https://openalex.org/W4396821195","https://openalex.org/W4400526199","https://openalex.org/W4412377829","https://openalex.org/W4416035733","https://openalex.org/W4416036880","https://openalex.org/W7167903019"],"related_works":[],"abstract_inverted_index":{"Recent":[0],"work":[1],"on":[2,91],"neural":[3],"sparse":[4],"retrieval":[5,48,122],"has":[6],"demonstrated":[7],"strong":[8],"relevance":[9],"by":[10,107],"leveraging":[11],"Large":[12],"Language":[13],"Models":[14],"(LLMs)":[15],"for":[16,58],"semantic":[17],"term":[18],"expansion.":[19],"However,":[20],"learned":[21],"models":[22],"paired":[23],"with":[24,88],"previous":[25],"sparsification":[26],"techniques":[27],"still":[28],"yield":[29],"overly":[30],"long":[31],"document":[32,84,114],"and":[33,50,74,83,95,113,124],"query":[34,82,112],"vectors":[35],"partly":[36],"due":[37],"to":[38,47,77],"a":[39,44,56,63],"large":[40],"LLM":[41],"vocabulary,":[42],"imposing":[43],"serious":[45],"challenge":[46],"time":[49],"space":[51],"efficiency.":[52],"This":[53],"paper":[54],"proposes":[55],"scheme":[57,102,117],"optimizing":[59],"model":[60,90],"sparsity":[61,80],"through":[62],"synergy":[64],"of":[65,81],"adaptive":[66],"strategies,":[67],"including":[68],"learnable":[69],"soft":[70],"top-??,":[71],"per-term":[72],"thresholding,":[73],"FLOPs":[75],"regularization":[76],"increase":[78],"the":[79,92,100,105,110],"vectors.":[85],"Experimental":[86],"results":[87],"Lion-SP":[89],"MS":[93],"MARCO":[94],"BEIR":[96],"datasets":[97],"demonstrate":[98],"that":[99],"proposed":[101],"can":[103,118],"outperform":[104],"baselines":[106],"significantly":[108],"reducing":[109],"average":[111],"lengths.":[115],"Our":[116],"achieve":[119],"much":[120],"shorter":[121],"latency":[123],"lower":[125],"storage":[126],"cost":[127],"while":[128],"maintaining":[129],"highly":[130],"competitive":[131],"relevance.":[132]},"counts_by_year":[],"updated_date":"2026-07-11T05:49:48.208612","created_date":"2026-07-11T00:00:00"}