{"id":"https://openalex.org/W7220667693","doi":"https://doi.org/10.48550/arxiv.2610.05540","title":"SALUS: Automated Auditing of NL-to-SQL Benchmarks through Weak Supervision of Multi-Agent Output","display_name":"SALUS: Automated Auditing of NL-to-SQL Benchmarks through Weak Supervision of Multi-Agent Output","publication_year":2026,"publication_date":"2026-10-04","ids":{"openalex":"https://openalex.org/W7220667693","doi":"https://doi.org/10.48550/arxiv.2610.05540"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2610.05540","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2610.05540","pdf_url":"https://arxiv.org/pdf/2610.05540","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"volume":null,"type":"preprint","is_traditional":true,"indexed_in":["arxiv","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2610.05540","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5143438949","display_name":"Shiyuan Zhou","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I204250578","display_name":"University of California, Irvine","ror":"https://ror.org/04gyf1771","country_code":"US","type":"education","lineage":["https://openalex.org/I204250578"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Zhou, Shiyuan","raw_affiliation_strings":["University of California , Irvine , USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of California , Irvine , USA","institution_ids":["https://openalex.org/I204250578"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5120273714","display_name":"Ashwin Gerard Colaco","orcid":"https://orcid.org/0000-0002-7370-2148","observed_orcids":["https://orcid.org/0000-0002-7370-2148"]},"institutions":[{"id":"https://openalex.org/I204250578","display_name":"University of California, Irvine","ror":"https://ror.org/04gyf1771","country_code":"US","type":"education","lineage":["https://openalex.org/I204250578"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Colaco, Ashwin Gerard","raw_affiliation_strings":["University of California , Irvine , USA SAINYAM GALHOTRA ,"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of California , Irvine , USA SAINYAM GALHOTRA ,","institution_ids":["https://openalex.org/I204250578"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5038532934","display_name":"Sainyam Galhotra","orcid":"https://orcid.org/0000-0003-2529-4036","observed_orcids":["https://orcid.org/0000-0003-2529-4036"]},"institutions":[{"id":"https://openalex.org/I204250578","display_name":"University of California, Irvine","ror":"https://ror.org/04gyf1771","country_code":"US","type":"education","lineage":["https://openalex.org/I204250578"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Galhotra, Sainyam","raw_affiliation_strings":["University of California , Irvine , USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of California , Irvine , USA","institution_ids":["https://openalex.org/I204250578"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5010114060","display_name":"Sharad Mehrotra","orcid":"https://orcid.org/0000-0003-1667-5435","observed_orcids":["https://orcid.org/0000-0003-1667-5435"]},"institutions":[{"id":"https://openalex.org/I204250578","display_name":"University of California, Irvine","ror":"https://ror.org/04gyf1771","country_code":"US","type":"education","lineage":["https://openalex.org/I204250578"]},{"id":"https://openalex.org/I205783295","display_name":"Cornell University","ror":"https://ror.org/05bnh6r87","country_code":"US","type":"education","lineage":["https://openalex.org/I205783295"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Mehrotra, Sharad","raw_affiliation_strings":["Cornell University , Ithaca , New York , USA;","University of California , Irvine , Irvine , California , USA;"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Cornell University , Ithaca , New York , USA;","institution_ids":["https://openalex.org/I205783295"]},{"raw_affiliation_string":"University of California , Irvine , Irvine , California , USA;","institution_ids":["https://openalex.org/I204250578"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.7246000170707703,"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"}},"topics":[{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.7246000170707703,"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":0.10329999774694443,"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/T12535","display_name":"Machine Learning and Data Classification","score":0.04320000112056732,"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/annotation-error-detection","display_name":"annotation error detection","score":0.8500000238418579},{"id":"https://openalex.org/keywords/weakly-supervised-learning","display_name":"weakly supervised learning","score":0.9440000057220459},{"id":"https://openalex.org/keywords/noisy-label-learning","display_name":"noisy label learning","score":0.3930000066757202},{"id":"https://openalex.org/keywords/bird-benchmark","display_name":"BIRD benchmark","score":0.6060000061988831},{"id":"https://openalex.org/keywords/spider-benchmark","display_name":"Spider benchmark","score":0.9639999866485596}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7973999977111816},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.7206000089645386},{"id":"https://openalex.org/C2776321320","wikidata":"https://www.wikidata.org/wiki/Q857525","display_name":"Annotation","level":2,"score":0.6236000061035156},{"id":"https://openalex.org/C510870499","wikidata":"https://www.wikidata.org/wiki/Q47607","display_name":"SQL","level":2,"score":0.6083999872207642},{"id":"https://openalex.org/C79581498","wikidata":"https://www.wikidata.org/wiki/Q1367530","display_name":"Suite","level":2,"score":0.4948999881744385},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.48590001463890076},{"id":"https://openalex.org/C168065819","wikidata":"https://www.wikidata.org/wiki/Q845566","display_name":"Debugging","level":2,"score":0.47699999809265137},{"id":"https://openalex.org/C55439883","wikidata":"https://www.wikidata.org/wiki/Q360812","display_name":"Correctness","level":2,"score":0.46299999952316284},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.45210000872612},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4438000023365021},{"id":"https://openalex.org/C43214815","wikidata":"https://www.wikidata.org/wiki/Q7310987","display_name":"Reliability (semiconductor)","level":3,"score":0.4293000102043152},{"id":"https://openalex.org/C132964779","wikidata":"https://www.wikidata.org/wiki/Q2110223","display_name":"Raw data","level":2,"score":0.35199999809265137},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.34610000252723694},{"id":"https://openalex.org/C103088060","wikidata":"https://www.wikidata.org/wiki/Q1062839","display_name":"Error detection and correction","level":2,"score":0.33880001306533813},{"id":"https://openalex.org/C63000827","wikidata":"https://www.wikidata.org/wiki/Q3080428","display_name":"Software portability","level":2,"score":0.3140999972820282},{"id":"https://openalex.org/C52001869","wikidata":"https://www.wikidata.org/wiki/Q812530","display_name":"Naive Bayes classifier","level":3,"score":0.3073999881744385},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.30160000920295715},{"id":"https://openalex.org/C115901376","wikidata":"https://www.wikidata.org/wiki/Q184199","display_name":"Automation","level":2,"score":0.2980000078678131},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.28369998931884766},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.2791000008583069},{"id":"https://openalex.org/C2777904410","wikidata":"https://www.wikidata.org/wiki/Q7397","display_name":"Software","level":2,"score":0.27549999952316284},{"id":"https://openalex.org/C107673813","wikidata":"https://www.wikidata.org/wiki/Q812534","display_name":"Bayesian probability","level":2,"score":0.27459999918937683},{"id":"https://openalex.org/C86251818","wikidata":"https://www.wikidata.org/wiki/Q816754","display_name":"Benchmarking","level":2,"score":0.2728999853134155},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.2632000148296356},{"id":"https://openalex.org/C199521495","wikidata":"https://www.wikidata.org/wiki/Q181487","display_name":"Audit","level":2,"score":0.25589999556541443},{"id":"https://openalex.org/C167966045","wikidata":"https://www.wikidata.org/wiki/Q5532625","display_name":"Generative model","level":3,"score":0.2547999918460846},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.25380000472068787}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2610.05540","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2610.05540","pdf_url":"https://arxiv.org/pdf/2610.05540","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2610.05540","doi":"https://doi.org/10.48550/arxiv.2610.05540","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2610.05540","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2610.05540","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2610.05540","pdf_url":"https://arxiv.org/pdf/2610.05540","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7220667693.pdf","grobid_xml":"https://content.openalex.org/works/W7220667693.grobid-xml"},"referenced_works_count":10,"referenced_works":["https://openalex.org/W2016023958","https://openalex.org/W2952865802","https://openalex.org/W3200496214","https://openalex.org/W4387561453","https://openalex.org/W4392822190","https://openalex.org/W4404406411","https://openalex.org/W4411403493","https://openalex.org/W4415795567","https://openalex.org/W4417301601","https://openalex.org/W7160251331"],"related_works":["https://openalex.org/W7155190575","https://openalex.org/W4412877147","https://openalex.org/W4416075866","https://openalex.org/W7155039818","https://openalex.org/W7161847287","https://openalex.org/W7160379233","https://openalex.org/W7138917001","https://openalex.org/W7156057422","https://openalex.org/W7208712719","https://openalex.org/W7092290296"],"abstract_inverted_index":{"Natural":[0],"language":[1],"to":[2,8,113,118,159],"SQL":[3,67,110],"(NL-to-SQL)":[4],"benchmarks":[5,21],"are":[6],"foundational":[7],"progress":[9],"in":[10,54],"data":[11],"analysis":[12],"research,":[13],"yet":[14],"recent":[15],"work":[16],"has":[17],"shown":[18],"that":[19,49,107],"widely-used":[20],"contain":[22],"significant":[23],"annotation":[24,52,166],"errors.":[25],"These":[26,101],"errors":[27,53],"silently":[28],"corrupt":[29],"evaluation":[30],"metrics,":[31],"penalize":[32],"correct":[33],"model":[34],"output,":[35],"and":[36,174],"distort":[37],"the":[38,154,160],"field's":[39],"understanding":[40],"of":[41,76,137,169],"state-of-the-art":[42,155],"performance.":[43],"We":[44,131],"present":[45],"SALUS,":[46],"a":[47,62,74,87,104,135],"system":[48],"automatically":[50],"detects":[51],"NL-to-SQL":[55],"benchmarks.":[56],"SALUS":[57,117,147,158],"frames":[58],"benchmark":[59,128,136],"auditing":[60],"as":[61],"weakly":[63],"supervised":[64],"error":[65,129,167],"detection:":[66],"generated":[68],"by":[69],"multiple":[70],"LLM":[71],"agents":[72],"drive":[73],"suite":[75],"complementary":[77],"weak-labeling":[78],"functions.":[79],"By":[80],"passing":[81],"this":[82],"noisy":[83],"vote":[84],"matrix":[85],"through":[86],"generative":[88],"label":[89],"model,":[90],"we":[91,164],"extract":[92],"high-confidence":[93],"training":[94],"samples":[95,102],"without":[96],"requiring":[97],"human":[98],"ground":[99],"truth.":[100],"train":[103],"decision":[105],"plane":[106],"maps":[108],"gold":[109],"query":[111],"features":[112],"per-agent":[114],"trustworthiness,":[115],"allowing":[116],"intelligently":[119],"fuse":[120],"reliability":[121],"estimates":[122],"with":[123,142],"raw":[124],"verdicts":[125],"for":[126],"rigorous":[127],"detection.":[130],"evaluate":[132],"on":[133,172,176],"BIRD-Clean-xs,":[134],"298":[138],"BIRD":[139,173],"development":[140,162],"tasks":[141],"manually":[143],"verified":[144],"correctness":[145],"labels.":[146],"achieves":[148],"F1":[149],"=":[150],"0.9194,":[151],"significantly":[152],"outperforming":[153],"baselines.":[156],"Applying":[157],"full":[161],"sets,":[163],"estimate":[165],"rates":[168],"approximately":[170],"37%":[171],"27%":[175],"Spider.":[177]},"counts_by_year":[],"updated_date":"2026-11-07T11:25:07.637180","created_date":"2026-10-07T00:00:00"}