{"id":"https://openalex.org/W4411374433","doi":"https://doi.org/10.1145/3722212.3725130","title":"ScaleLLM: A Technique for Scalable LLM-augmented Data Systems","display_name":"ScaleLLM: A Technique for Scalable LLM-augmented Data Systems","publication_year":2025,"publication_date":"2025-06-17","ids":{"openalex":"https://openalex.org/W4411374433","doi":"https://doi.org/10.1145/3722212.3725130"},"language":"en","primary_location":{"id":"doi:10.1145/3722212.3725130","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3722212.3725130","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Companion of the 2025 International Conference on Management of Data","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5118382452","display_name":"Ashwin Alaparthi","orcid":"https://orcid.org/0009-0004-7889-1082"},"institutions":[{"id":"https://openalex.org/I79576946","display_name":"University of Pennsylvania","ror":"https://ror.org/00b30xv10","country_code":"US","type":"education","lineage":["https://openalex.org/I79576946"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ashwin Alaparthi","raw_affiliation_strings":["University of Pennsylvania, Philadelphia, PA, USA"],"raw_orcid":"https://orcid.org/0009-0004-7889-1082","affiliations":[{"raw_affiliation_string":"University of Pennsylvania, Philadelphia, PA, USA","institution_ids":["https://openalex.org/I79576946"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5118273616","display_name":"Paul Loh","orcid":null},"institutions":[{"id":"https://openalex.org/I79576946","display_name":"University of Pennsylvania","ror":"https://ror.org/00b30xv10","country_code":"US","type":"education","lineage":["https://openalex.org/I79576946"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Paul Loh","raw_affiliation_strings":["University of Pennsylvania, Philadelphia, PA, USA"],"raw_orcid":"https://orcid.org/0009-0009-0640-2645","affiliations":[{"raw_affiliation_string":"University of Pennsylvania, Philadelphia, PA, USA","institution_ids":["https://openalex.org/I79576946"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5025731013","display_name":"Ryan Marcus","orcid":"https://orcid.org/0000-0002-1279-1124"},"institutions":[{"id":"https://openalex.org/I79576946","display_name":"University of Pennsylvania","ror":"https://ror.org/00b30xv10","country_code":"US","type":"education","lineage":["https://openalex.org/I79576946"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ryan Marcus","raw_affiliation_strings":["University of Pennsylvania, Philadelphia, PA, USA"],"raw_orcid":"https://orcid.org/0000-0002-1279-1124","affiliations":[{"raw_affiliation_string":"University of Pennsylvania, Philadelphia, PA, USA","institution_ids":["https://openalex.org/I79576946"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I79576946"],"apc_list":null,"apc_paid":null,"fwci":1.123,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.83165362,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":95,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"11","last_page":"14"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11704","display_name":"Mobile Crowdsensing and Crowdsourcing","score":0.9998999834060669,"subfield":{"id":"https://openalex.org/subfields/1706","display_name":"Computer Science Applications"},"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/T11704","display_name":"Mobile Crowdsensing and Crowdsourcing","score":0.9998999834060669,"subfield":{"id":"https://openalex.org/subfields/1706","display_name":"Computer Science Applications"},"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/T10764","display_name":"Privacy-Preserving Technologies in Data","score":0.994700014591217,"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/T12761","display_name":"Data Stream Mining Techniques","score":0.992900013923645,"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/computer-science","display_name":"Computer science","score":0.7383298277854919},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.7058547139167786},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.15369823575019836}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7383298277854919},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.7058547139167786},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.15369823575019836}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3722212.3725130","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3722212.3725130","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Companion of the 2025 International Conference on Management of Data","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":4,"referenced_works":["https://openalex.org/W2168144930","https://openalex.org/W2612560781","https://openalex.org/W2890484448","https://openalex.org/W3156414406"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W2390279801","https://openalex.org/W4391913857","https://openalex.org/W2358668433","https://openalex.org/W4396701345","https://openalex.org/W2376932109","https://openalex.org/W2001405890","https://openalex.org/W2389214306"],"abstract_inverted_index":{"Large":[0],"language":[1],"models":[2],"(LLMs)":[3],"offer":[4],"powerful":[5],"semantic":[6],"insights":[7],"for":[8,55,109],"data":[9,48],"analytics,":[10],"but":[11],"row-by-row":[12],"LLM":[13,73],"calls":[14],"quickly":[15],"become":[16],"prohibitively":[17],"expensive":[18],"in":[19,81,115],"large":[20],"datasets.":[21],"We":[22],"introduce":[23],"ScaleLLM,":[24],"a":[25,44,50,71],"novel":[26],"system":[27],"that":[28,69],"substantially":[29],"reduces":[30],"both":[31],"latency":[32],"and":[33,107],"cost":[34],"on":[35,43],"text":[36],"classification":[37],"tasks.":[38,83],"ScaleLLM":[39,84],"couples":[40],"LLM-generated":[41],"labels":[42],"small":[45],"subset":[46],"of":[47,70,78],"with":[49,111],"lightweight":[51],"machine":[52],"learning":[53],"model":[54],"large-scale":[56],"inference.":[57],"This":[58],"approach":[59],"provides":[60,86],"significant":[61],"speed-ups-up":[62],"to":[63,68],"37\u00d7-while":[64],"maintaining":[65],"accuracy":[66,80],"close":[67],"full":[72],"baseline,":[74],"converging":[75],"within":[76],"1%":[77],"its":[79],"several":[82],"also":[85],"cost-accuracy":[87],"trade-off":[88],"projections,":[89],"giving":[90],"users":[91],"fine-grained":[92],"control":[93],"over":[94],"performance":[95],"trade-offs.":[96],"Our":[97],"demonstration":[98],"illustrates":[99],"ScaleLLM's":[100],"reusable":[101],"embedding":[102],"views,":[103],"efficient":[104],"inference":[105],"architecture,":[106],"potential":[108],"integration":[110],"query":[112],"optimization":[113],"frameworks":[114],"LLM-augmented":[116],"database":[117],"systems.":[118]},"counts_by_year":[{"year":2026,"cited_by_count":1}],"updated_date":"2026-06-26T08:34:08.712188","created_date":"2025-10-10T00:00:00"}