{"id":"https://openalex.org/W4404181169","doi":"https://doi.org/10.14778/3685800.3685835","title":"spade: Synthesizing Data Quality Assertions for Large Language Model Pipelines","display_name":"spade: Synthesizing Data Quality Assertions for Large Language Model Pipelines","publication_year":2024,"publication_date":"2024-08-01","ids":{"openalex":"https://openalex.org/W4404181169","doi":"https://doi.org/10.14778/3685800.3685835"},"language":"en","primary_location":{"id":"doi:10.14778/3685800.3685835","is_oa":false,"landing_page_url":"https://doi.org/10.14778/3685800.3685835","pdf_url":null,"source":{"id":"https://openalex.org/S4210226185","display_name":"Proceedings of the VLDB Endowment","issn_l":"2150-8097","issn":["2150-8097"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the VLDB Endowment","raw_type":"journal-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/A5023956968","display_name":"Shreya Shankar","orcid":"https://orcid.org/0000-0002-0919-9672"},"institutions":[{"id":"https://openalex.org/I134446601","display_name":"Berkeley College","ror":"https://ror.org/02xewxa75","country_code":"US","type":"education","lineage":["https://openalex.org/I134446601"]},{"id":"https://openalex.org/I95457486","display_name":"University of California, Berkeley","ror":"https://ror.org/01an7q238","country_code":"US","type":"education","lineage":["https://openalex.org/I95457486"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Shreya Shankar","raw_affiliation_strings":["UC Berkeley"],"affiliations":[{"raw_affiliation_string":"UC Berkeley","institution_ids":["https://openalex.org/I134446601","https://openalex.org/I95457486"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100397330","display_name":"Haotian Li","orcid":"https://orcid.org/0000-0001-9547-3449"},"institutions":[{"id":"https://openalex.org/I200769079","display_name":"Hong Kong University of Science and Technology","ror":"https://ror.org/00q4vv597","country_code":"HK","type":"education","lineage":["https://openalex.org/I200769079"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Haotian Li","raw_affiliation_strings":["HKUST"],"affiliations":[{"raw_affiliation_string":"HKUST","institution_ids":["https://openalex.org/I200769079"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5092622495","display_name":"Parth Asawa","orcid":null},"institutions":[{"id":"https://openalex.org/I134446601","display_name":"Berkeley College","ror":"https://ror.org/02xewxa75","country_code":"US","type":"education","lineage":["https://openalex.org/I134446601"]},{"id":"https://openalex.org/I95457486","display_name":"University of California, Berkeley","ror":"https://ror.org/01an7q238","country_code":"US","type":"education","lineage":["https://openalex.org/I95457486"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Parth Asawa","raw_affiliation_strings":["UC Berkeley"],"affiliations":[{"raw_affiliation_string":"UC Berkeley","institution_ids":["https://openalex.org/I134446601","https://openalex.org/I95457486"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5058441702","display_name":"Madelon Hulsebos","orcid":"https://orcid.org/0000-0002-0949-7290"},"institutions":[{"id":"https://openalex.org/I134446601","display_name":"Berkeley College","ror":"https://ror.org/02xewxa75","country_code":"US","type":"education","lineage":["https://openalex.org/I134446601"]},{"id":"https://openalex.org/I95457486","display_name":"University of California, Berkeley","ror":"https://ror.org/01an7q238","country_code":"US","type":"education","lineage":["https://openalex.org/I95457486"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Madelon Hulsebos","raw_affiliation_strings":["UC Berkeley"],"affiliations":[{"raw_affiliation_string":"UC Berkeley","institution_ids":["https://openalex.org/I134446601","https://openalex.org/I95457486"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5091648568","display_name":"Yiming Lin","orcid":"https://orcid.org/0000-0001-6792-2155"},"institutions":[{"id":"https://openalex.org/I134446601","display_name":"Berkeley College","ror":"https://ror.org/02xewxa75","country_code":"US","type":"education","lineage":["https://openalex.org/I134446601"]},{"id":"https://openalex.org/I95457486","display_name":"University of California, Berkeley","ror":"https://ror.org/01an7q238","country_code":"US","type":"education","lineage":["https://openalex.org/I95457486"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yiming Lin","raw_affiliation_strings":["UC Berkeley"],"affiliations":[{"raw_affiliation_string":"UC Berkeley","institution_ids":["https://openalex.org/I134446601","https://openalex.org/I95457486"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5065870025","display_name":"J.D. Zamfirescu-Pereira","orcid":"https://orcid.org/0000-0002-5310-6728"},"institutions":[{"id":"https://openalex.org/I134446601","display_name":"Berkeley College","ror":"https://ror.org/02xewxa75","country_code":"US","type":"education","lineage":["https://openalex.org/I134446601"]},{"id":"https://openalex.org/I95457486","display_name":"University of California, Berkeley","ror":"https://ror.org/01an7q238","country_code":"US","type":"education","lineage":["https://openalex.org/I95457486"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"J. D. Zamfirescu-Pereira","raw_affiliation_strings":["UC Berkeley"],"affiliations":[{"raw_affiliation_string":"UC Berkeley","institution_ids":["https://openalex.org/I134446601","https://openalex.org/I95457486"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5076226272","display_name":"Harrison Chase","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Harrison Chase","raw_affiliation_strings":["LangChain"],"affiliations":[{"raw_affiliation_string":"LangChain","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5093673285","display_name":"Will Fu-Hinthorn","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Will Fu-Hinthorn","raw_affiliation_strings":["LangChain"],"affiliations":[{"raw_affiliation_string":"LangChain","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5013608601","display_name":"Aditya Parameswaran","orcid":"https://orcid.org/0000-0002-4538-4752"},"institutions":[{"id":"https://openalex.org/I134446601","display_name":"Berkeley College","ror":"https://ror.org/02xewxa75","country_code":"US","type":"education","lineage":["https://openalex.org/I134446601"]},{"id":"https://openalex.org/I95457486","display_name":"University of California, Berkeley","ror":"https://ror.org/01an7q238","country_code":"US","type":"education","lineage":["https://openalex.org/I95457486"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Aditya G. Parameswaran","raw_affiliation_strings":["UC Berkeley"],"affiliations":[{"raw_affiliation_string":"UC Berkeley","institution_ids":["https://openalex.org/I134446601","https://openalex.org/I95457486"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5049016095","display_name":"Eugene Wu","orcid":"https://orcid.org/0000-0003-4254-6688"},"institutions":[{"id":"https://openalex.org/I78577930","display_name":"Columbia University","ror":"https://ror.org/00hj8s172","country_code":"US","type":"education","lineage":["https://openalex.org/I78577930"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Eugene Wu","raw_affiliation_strings":["Columbia University"],"affiliations":[{"raw_affiliation_string":"Columbia University","institution_ids":["https://openalex.org/I78577930"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":10,"corresponding_author_ids":["https://openalex.org/A5023956968"],"corresponding_institution_ids":["https://openalex.org/I134446601","https://openalex.org/I95457486"],"apc_list":null,"apc_paid":null,"fwci":8.5717,"has_fulltext":false,"cited_by_count":18,"citation_normalized_percentile":{"value":0.97928556,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":96,"max":100},"biblio":{"volume":"17","issue":"12","first_page":"4173","last_page":"4186"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11719","display_name":"Data Quality and Management","score":0.9998999834060669,"subfield":{"id":"https://openalex.org/subfields/1803","display_name":"Management Science and Operations Research"},"field":{"id":"https://openalex.org/fields/18","display_name":"Decision Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},"topics":[{"id":"https://openalex.org/T11719","display_name":"Data Quality and Management","score":0.9998999834060669,"subfield":{"id":"https://openalex.org/subfields/1803","display_name":"Management Science and Operations Research"},"field":{"id":"https://openalex.org/fields/18","display_name":"Decision Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T10215","display_name":"Semantic Web and Ontologies","score":0.9987000226974487,"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/T10028","display_name":"Topic Modeling","score":0.9972000122070312,"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":0.6779128909111023},{"id":"https://openalex.org/keywords/pipeline-transport","display_name":"Pipeline transport","score":0.5191168785095215},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.4964459538459778},{"id":"https://openalex.org/keywords/quality","display_name":"Quality (philosophy)","score":0.49325937032699585},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.13508164882659912},{"id":"https://openalex.org/keywords/philosophy","display_name":"Philosophy","score":0.064616858959198},{"id":"https://openalex.org/keywords/epistemology","display_name":"Epistemology","score":0.0563541054725647},{"id":"https://openalex.org/keywords/mechanical-engineering","display_name":"Mechanical engineering","score":0.05431291460990906}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6779128909111023},{"id":"https://openalex.org/C175309249","wikidata":"https://www.wikidata.org/wiki/Q725864","display_name":"Pipeline transport","level":2,"score":0.5191168785095215},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.4964459538459778},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.49325937032699585},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.13508164882659912},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.064616858959198},{"id":"https://openalex.org/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","level":1,"score":0.0563541054725647},{"id":"https://openalex.org/C78519656","wikidata":"https://www.wikidata.org/wiki/Q101333","display_name":"Mechanical engineering","level":1,"score":0.05431291460990906}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.14778/3685800.3685835","is_oa":false,"landing_page_url":"https://doi.org/10.14778/3685800.3685835","pdf_url":null,"source":{"id":"https://openalex.org/S4210226185","display_name":"Proceedings of the VLDB Endowment","issn_l":"2150-8097","issn":["2150-8097"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the VLDB Endowment","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Industry, innovation and infrastructure","score":0.5899999737739563,"id":"https://metadata.un.org/sdg/9"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":26,"referenced_works":["https://openalex.org/W1532421987","https://openalex.org/W2489773810","https://openalex.org/W2889249015","https://openalex.org/W2905588001","https://openalex.org/W2948447697","https://openalex.org/W2952490857","https://openalex.org/W3009065172","https://openalex.org/W3027879771","https://openalex.org/W3037887271","https://openalex.org/W3045754299","https://openalex.org/W3104128335","https://openalex.org/W3105684693","https://openalex.org/W3185341429","https://openalex.org/W3203321135","https://openalex.org/W4210354100","https://openalex.org/W4221143046","https://openalex.org/W4221149006","https://openalex.org/W4225080353","https://openalex.org/W4235216760","https://openalex.org/W4366548330","https://openalex.org/W4378908626","https://openalex.org/W4379390538","https://openalex.org/W4384304865","https://openalex.org/W4386128198","https://openalex.org/W4387841511","https://openalex.org/W4387848581"],"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/W4396696052"],"abstract_inverted_index":{"Large":[0],"language":[1],"models":[2],"(LLMs)":[3],"are":[4,27],"being":[5],"increasingly":[6],"deployed":[7,160],"as":[8,161],"part":[9],"of":[10,18,40,106,142,186],"pipelines":[11,182],"that":[12,34,67,76,122],"repeatedly":[13],"process":[14],"or":[15],"generate":[16,175],"data":[17,45,64,80,176],"some":[19],"sort.":[20],"However,":[21],"a":[22,59,119,184],"common":[23],"barrier":[24],"to":[25,48,86,90,96,111,154,174],"deployment":[26],"the":[28,38,74,97,140],"frequent":[29],"and":[30,88,116,126,146,170],"often":[31,78],"unpredictable":[32],"errors":[33],"plague":[35],"LLMs.":[36],"Acknowledging":[37],"inevitability":[39],"these":[41],"errors,":[42],"we":[43],"propose":[44],"quality":[46,65,81,177],"assertions":[47,66,143,178],"identify":[49,68,79],"when":[50,152],"LLMs":[51],"may":[52],"be":[53],"making":[54],"mistakes.":[55],"We":[56,72],"present":[57],"spade,":[58],"method":[60],"for":[61,179],"automatically":[62],"synthesizing":[63],"bad":[69],"LLM":[70,98,135,167],"outputs.":[71],"make":[73],"observation":[75],"developers":[77],"issues":[82],"during":[83],"prototyping":[84],"prior":[85],"deployment,":[87],"attempt":[89],"address":[91],"them":[92],"by":[93,144,150],"adding":[94],"instructions":[95],"prompt":[99,107],"over":[100,109,180],"time.":[101],"spade":[102,137,157],"therefore":[103],"analyzes":[104],"histories":[105],"versions":[108],"time":[110],"create":[112],"candidate":[113],"assertion":[114],"functions":[115],"then":[117],"selects":[118],"minimal":[120],"set":[121],"fulfills":[123],"both":[124],"coverage":[125],"accuracy":[127],"requirements.":[128],"In":[129],"testing":[130],"across":[131,183],"nine":[132],"different":[133],"real-world":[134],"pipelines,":[136],"efficiently":[138],"reduces":[139],"number":[141],"14%":[145],"decreases":[147],"false":[148],"failures":[149],"21%":[151],"compared":[153],"simpler":[155],"baselines.":[156],"has":[158,171],"been":[159,172],"an":[162],"offering":[163],"within":[164],"LangSmith,":[165],"LangChain's":[166],"pipeline":[168],"hub,":[169],"used":[173],"2000":[181],"spectrum":[185],"industries.":[187]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":17}],"updated_date":"2026-04-15T08:11:43.952461","created_date":"2025-10-10T00:00:00"}