{"id":"https://openalex.org/W7168367179","doi":"https://doi.org/10.1145/3805712.3809708","title":"Scaling Laws for Embedding Dimension in Information Retrieval","display_name":"Scaling Laws for Embedding Dimension in Information Retrieval","publication_year":2026,"publication_date":"2026-07-15","ids":{"openalex":"https://openalex.org/W7168367179","doi":"https://doi.org/10.1145/3805712.3809708"},"language":null,"primary_location":{"id":"doi:10.1145/3805712.3809708","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3805712.3809708","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":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.1145/3805712.3809708","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5140883638","display_name":"Julian Killingback","orcid":"https://orcid.org/0000-0003-2280-8759"},"institutions":[{"id":"https://openalex.org/I24603500","display_name":"University of Massachusetts Amherst","ror":"https://ror.org/0072zz521","country_code":"US","type":"education","lineage":["https://openalex.org/I24603500"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Julian Killingback","raw_affiliation_strings":["Center for Intelligent Information Retrieval, University of Massachusetts Amherst, Amherst, MA, USA"],"raw_orcid":"https://orcid.org/0000-0003-2280-8759","affiliations":[{"raw_affiliation_string":"Center for Intelligent Information Retrieval, University of Massachusetts Amherst, Amherst, MA, USA","institution_ids":["https://openalex.org/I24603500"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5140780711","display_name":"Mahta Rafiee","orcid":"https://orcid.org/0009-0007-1410-4897"},"institutions":[{"id":"https://openalex.org/I24603500","display_name":"University of Massachusetts Amherst","ror":"https://ror.org/0072zz521","country_code":"US","type":"education","lineage":["https://openalex.org/I24603500"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Mahta Rafiee","raw_affiliation_strings":["Center for Intelligent Information Retrieval, University of Massachusetts Amherst, Amherst, MA, USA"],"raw_orcid":"https://orcid.org/0009-0007-1410-4897","affiliations":[{"raw_affiliation_string":"Center for Intelligent Information Retrieval, University of Massachusetts Amherst, Amherst, MA, USA","institution_ids":["https://openalex.org/I24603500"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5140764615","display_name":"Madine Manas","orcid":"https://orcid.org/0009-0008-2744-7001"},"institutions":[{"id":"https://openalex.org/I24603500","display_name":"University of Massachusetts Amherst","ror":"https://ror.org/0072zz521","country_code":"US","type":"education","lineage":["https://openalex.org/I24603500"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Madine Manas","raw_affiliation_strings":["Center for Intelligent Information Retrieval, University of Massachusetts Amherst, Amherst, MA, USA"],"raw_orcid":"https://orcid.org/0009-0008-2744-7001","affiliations":[{"raw_affiliation_string":"Center for Intelligent Information Retrieval, University of Massachusetts Amherst, Amherst, MA, USA","institution_ids":["https://openalex.org/I24603500"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5140870383","display_name":"Hamed Zamani","orcid":"https://orcid.org/0000-0002-0800-3340"},"institutions":[{"id":"https://openalex.org/I24603500","display_name":"University of Massachusetts Amherst","ror":"https://ror.org/0072zz521","country_code":"US","type":"education","lineage":["https://openalex.org/I24603500"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Hamed Zamani","raw_affiliation_strings":["Center for Intelligent Information Retrieval, University of Massachusetts Amherst, Amherst, MA, USA"],"raw_orcid":"https://orcid.org/0000-0002-0800-3340","affiliations":[{"raw_affiliation_string":"Center for Intelligent Information Retrieval, University of Massachusetts Amherst, Amherst, MA, USA","institution_ids":["https://openalex.org/I24603500"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I24603500"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"790","last_page":"800"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":null,"topics":[],"keywords":[{"id":"https://openalex.org/keywords/dimension","display_name":"Dimension (graph theory)","score":0.5189999938011169},{"id":"https://openalex.org/keywords/embedding","display_name":"Embedding","score":0.5054000020027161},{"id":"https://openalex.org/keywords/scaling","display_name":"Scaling","score":0.38100001215934753},{"id":"https://openalex.org/keywords/scaling-law","display_name":"Scaling law","score":0.3734999895095825},{"id":"https://openalex.org/keywords/relevance","display_name":"Relevance (law)","score":0.34439998865127563},{"id":"https://openalex.org/keywords/phase-retrieval","display_name":"Phase retrieval","score":0.30790001153945923}],"concepts":[{"id":"https://openalex.org/C33676613","wikidata":"https://www.wikidata.org/wiki/Q13415176","display_name":"Dimension (graph theory)","level":2,"score":0.5189999938011169},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.5054000020027161},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.47360000014305115},{"id":"https://openalex.org/C99844830","wikidata":"https://www.wikidata.org/wiki/Q102441924","display_name":"Scaling","level":2,"score":0.38100001215934753},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.3774999976158142},{"id":"https://openalex.org/C2988430800","wikidata":"https://www.wikidata.org/wiki/Q428971","display_name":"Scaling law","level":3,"score":0.3734999895095825},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.3723999857902527},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.36079999804496765},{"id":"https://openalex.org/C158154518","wikidata":"https://www.wikidata.org/wiki/Q7310970","display_name":"Relevance (law)","level":2,"score":0.34439998865127563},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3416000008583069},{"id":"https://openalex.org/C81793267","wikidata":"https://www.wikidata.org/wiki/Q7180962","display_name":"Phase retrieval","level":3,"score":0.30790001153945923},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.29789999127388},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.2944999933242798},{"id":"https://openalex.org/C161156560","wikidata":"https://www.wikidata.org/wiki/Q1638872","display_name":"Document retrieval","level":2,"score":0.27900001406669617},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.27720001339912415},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.2678999900817871},{"id":"https://openalex.org/C70518039","wikidata":"https://www.wikidata.org/wiki/Q16000077","display_name":"Dimensionality reduction","level":2,"score":0.266400009393692},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.2644999921321869},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.2605000138282776},{"id":"https://openalex.org/C165064840","wikidata":"https://www.wikidata.org/wiki/Q1321061","display_name":"Matching (statistics)","level":2,"score":0.25529998540878296}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3805712.3809708","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3805712.3809708","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:10.1145/3805712.3809708","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3805712.3809708","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":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":22,"referenced_works":["https://openalex.org/W2027625319","https://openalex.org/W2124509324","https://openalex.org/W2897754576","https://openalex.org/W2963341956","https://openalex.org/W2979826702","https://openalex.org/W3099700870","https://openalex.org/W3153624757","https://openalex.org/W3157758108","https://openalex.org/W3196481040","https://openalex.org/W3206455169","https://openalex.org/W3217305727","https://openalex.org/W4206121183","https://openalex.org/W4390962868","https://openalex.org/W4392735885","https://openalex.org/W4393300516","https://openalex.org/W4408395322","https://openalex.org/W4412377829","https://openalex.org/W4412394904","https://openalex.org/W4414451943","https://openalex.org/W4414946174","https://openalex.org/W7133205253","https://openalex.org/W7133214597"],"related_works":[],"abstract_inverted_index":{"Dense":[0],"retrieval,":[1],"which":[2,68],"encodes":[3],"queries":[4],"and":[5,23,48,52,66,106,122,179,246,259,269],"documents":[6],"into":[7,241],"a":[8,113,128,139,153,172,253],"single":[9,64],"dense":[10,34,87],"vector,":[11],"has":[12,58],"become":[13],"the":[14,32,40,44,73,77,117,149,166,191,214,242],"dominant":[15],"neural":[16],"retrieval":[17,35,83,88,101,123],"approach":[18],"due":[19],"to":[20,63,72,98,137,158,196,262],"its":[21],"simplicity":[22],"compatibility":[24],"with":[25,190,203,213,224,227,266],"fast":[26],"approximate":[27],"nearest":[28],"neighbor":[29],"algorithms.":[30],"As":[31],"tasks":[33,188],"performs":[36],"grow":[37],"in":[38],"complexity,":[39],"fundamental":[41,97],"limitations":[42,61,243],"of":[43,79,116,130,142,244],"underlying":[45],"data":[46,208],"structure":[47],"similarity":[49],"metric---namely":[50],"vectors":[51,65],"inner-products---become":[53],"more":[54],"apparent.":[55],"Recent":[56],"work":[57,237],"shown":[59],"theoretical":[60],"inherent":[62],"inner-products,":[67],"are":[69,210],"generally":[70],"tied":[71],"embedding":[74,80,92,120,143,167,177,199,229,260],"dimension.":[75],"Given":[76],"importance":[78],"dimension":[81,93,121,178,261],"for":[82,162,176,186,231,256],"capacity,":[84],"understanding":[85],"how":[86],"performance":[89,163,194,220,225,265],"changes":[90],"as":[91,169,171,198,249,251],"is":[94,96,221],"scaled":[95],"building":[99],"next-generation":[100],"models":[102],"that":[103,148,185,209,219],"balance":[104],"effectiveness":[105],"efficiency.":[107],"In":[108],"this":[109],"work,":[110],"we":[111,217],"conduct":[112],"comprehensive":[114],"analysis":[115,183],"relationship":[118],"between":[119],"performance.":[124],"Our":[125,182],"experiments":[126],"include":[127],"range":[129],"model":[131,135,180,258],"sizes":[132],"from":[133],"two":[134],"families":[136],"construct":[138],"detailed":[140],"picture":[141],"scaling":[144,150,160],"behavior.":[145],"We":[146,234],"find":[147,218],"behavior":[151,248],"fits":[152],"power":[154],"law,":[155],"allowing":[156],"us":[157],"derive":[159],"laws":[161],"given":[164],"only":[165],"dimension,":[168],"well":[170,250],"joint":[173],"law":[174],"accounting":[175],"size.":[181],"shows":[184],"evaluation":[187,207],"aligned":[189,212],"training":[192,215],"task,":[193,216],"continues":[195],"improve":[197],"size":[200],"increases,":[201],"though":[202],"diminishing":[204],"returns.":[205],"For":[206],"less":[211,222],"predictable,":[223],"degrading":[226],"larger":[228],"dimensions":[230],"certain":[232],"tasks.":[233],"hope":[235],"our":[236],"provides":[238],"additional":[239],"insight":[240],"embeddings":[245],"their":[247],"offers":[252],"practical":[254],"guide":[255],"selecting":[257],"achieve":[263],"optimal":[264],"reduced":[267],"storage":[268],"compute":[270],"costs.":[271]},"counts_by_year":[],"updated_date":"2026-07-17T05:52:16.776730","created_date":"2026-07-16T00:00:00"}