{"id":"https://openalex.org/W7162645548","doi":"https://doi.org/10.1145/3774905.3795600","title":"Train Large-Use Small: Optimizing within the Theoretical Limits of Embedding-based Retrieval","display_name":"Train Large-Use Small: Optimizing within the Theoretical Limits of Embedding-based Retrieval","publication_year":2026,"publication_date":"2026-05-28","ids":{"openalex":"https://openalex.org/W7162645548","doi":"https://doi.org/10.1145/3774905.3795600"},"language":null,"primary_location":{"id":"doi:10.1145/3774905.3795600","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3774905.3795600","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":"Companion Proceedings of the ACM Web Conference 2026","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.1145/3774905.3795600","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5040063710","display_name":"Sourav Dutta","orcid":"https://orcid.org/0000-0001-5722-7909"},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Sourav Dutta","raw_affiliation_strings":["Huawei Research Centre, Dublin, Ireland"],"raw_orcid":"https://orcid.org/0000-0002-8934-9166","affiliations":[{"raw_affiliation_string":"Huawei Research Centre, Dublin, Ireland","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":["https://openalex.org/A5040063710"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.63806923,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"346","last_page":"350"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10286","display_name":"Information Retrieval and Search Behavior","score":0.16619999706745148,"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":0.16619999706745148,"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/T11568","display_name":"Railway Systems and Energy Efficiency","score":0.042399998754262924,"subfield":{"id":"https://openalex.org/subfields/2209","display_name":"Industrial and Manufacturing Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T11942","display_name":"Transportation and Mobility Innovations","score":0.022099999710917473,"subfield":{"id":"https://openalex.org/subfields/2203","display_name":"Automotive Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.351500004529953},{"id":"https://openalex.org/keywords/limit","display_name":"Limit (mathematics)","score":0.3490999937057495},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.27900001406669617},{"id":"https://openalex.org/keywords/term","display_name":"Term (time)","score":0.24690000712871552},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.24420000612735748}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.579200029373169},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3799999952316284},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.351500004529953},{"id":"https://openalex.org/C151201525","wikidata":"https://www.wikidata.org/wiki/Q177239","display_name":"Limit (mathematics)","level":2,"score":0.3490999937057495},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.27900001406669617},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.2718999981880188},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.25440001487731934},{"id":"https://openalex.org/C61797465","wikidata":"https://www.wikidata.org/wiki/Q1188986","display_name":"Term (time)","level":2,"score":0.24690000712871552},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.24420000612735748},{"id":"https://openalex.org/C9652623","wikidata":"https://www.wikidata.org/wiki/Q190109","display_name":"Field (mathematics)","level":2,"score":0.2401999980211258}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3774905.3795600","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3774905.3795600","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":"Companion Proceedings of the ACM Web Conference 2026","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3774905.3795600","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3774905.3795600","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":"Companion Proceedings of the ACM Web Conference 2026","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":3,"referenced_works":["https://openalex.org/W2140095548","https://openalex.org/W3089621169","https://openalex.org/W4408338270"],"related_works":[],"abstract_inverted_index":{"Technology-Assisted":[0],"Review":[1],"(TAR)":[2],"systems":[3],"are":[4],"becoming":[5],"indispensable":[6],"in":[7,64],"specialized":[8],"domains":[9],"that":[10],"demand":[11],"extensive":[12],"document":[13,36],"retrieval":[14,79],"with":[15,94],"high":[16],"precision.":[17],"The":[18],"use":[19],"of":[20,30,54,74,86],"Large":[21],"Language":[22],"Models":[23],"(LLMs)":[24],"has":[25],"significantly":[26,83],"expanded":[27],"the":[28,71],"potential":[29],"TAR":[31],"systems,":[32],"for":[33,42],"handling":[34],"huge":[35],"corpora":[37],"to":[38],"extract":[39],"relevant":[40],"candidates":[41],"such":[43,75],"systems.":[44],"Semantic":[45],"similarity":[46],"or":[47],"relevance":[48],"using":[49],"high-dimensional":[50],"dense":[51],"vector":[52],"representations":[53],"input":[55],"text":[56],"from":[57],"large":[58],"models":[59,88],"forms":[60],"a":[61],"core":[62],"component":[63],"Information":[65],"Retrieval":[66],"tasks.":[67],"Recent":[68],"studies":[69],"on":[70,90],"theoretical":[72],"limitations":[73],"single-vector":[76],"embedding":[77],"based":[78],"approaches":[80],"have":[81],"showcased":[82],"poor":[84],"performance":[85],"state-of-the-art":[87],"even":[89],"small":[91],"retrieval-oriented":[92],"datasets":[93],"relatively":[95],"simple":[96],"queries.":[97]},"counts_by_year":[],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2026-05-29T00:00:00"}