{"id":"https://openalex.org/W7225273645","doi":"https://doi.org/10.5281/zenodo.23940768","title":"When the Semantic Layer Is Wrong: Do LLM Data Agents Follow or Flag Faulty Business Definitions?","display_name":"When the Semantic Layer Is Wrong: Do LLM Data Agents Follow or Flag Faulty Business Definitions?","publication_year":2026,"publication_date":"2026-11-04","ids":{"openalex":"https://openalex.org/W7225273645","doi":"https://doi.org/10.5281/zenodo.23940768"},"language":"en","primary_location":{"id":"doi:10.5281/zenodo.23940768","doi":"https://doi.org/10.5281/zenodo.23940768","is_oa":true,"landing_page_url":"https://doi.org/10.5281/zenodo.23940768","pdf_url":null,"source":{"id":"https://openalex.org/S4306400562","display_name":"Zenodo (CERN European Organization for Nuclear Research)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I67311998","host_organization_name":"European Organization for Nuclear Research","host_organization_lineage":["https://openalex.org/I67311998"],"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"},"volume":null,"type":"preprint","indexed_in":["datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://doi.org/10.5281/zenodo.23940768","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5160604506","display_name":"Poorva Barve","orcid":"https://orcid.org/0009-0009-0312-4125","observed_orcids":["https://orcid.org/0009-0009-0312-4125"]},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Barve, Poorva","raw_affiliation_strings":[],"raw_orcid":"https://orcid.org/0009-0009-0312-4125","affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":["https://openalex.org/A5160604506"],"corresponding_institution_ids":[],"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":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.21660000085830688,"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/T10028","display_name":"Topic Modeling","score":0.21660000085830688,"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/T10260","display_name":"Software Engineering Research","score":0.19679999351501465,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.13050000369548798,"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":[],"concepts":[{"id":"https://openalex.org/C2779227376","wikidata":"https://www.wikidata.org/wiki/Q6505497","display_name":"Layer (electronics)","level":2,"score":0.7087000012397766},{"id":"https://openalex.org/C56666940","wikidata":"https://www.wikidata.org/wiki/Q788790","display_name":"Documentation","level":2,"score":0.7013999819755554},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6001999974250793},{"id":"https://openalex.org/C199521495","wikidata":"https://www.wikidata.org/wiki/Q181487","display_name":"Audit","level":2,"score":0.5253999829292297},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.4823000133037567},{"id":"https://openalex.org/C2776291640","wikidata":"https://www.wikidata.org/wiki/Q2912517","display_name":"Value (mathematics)","level":2,"score":0.4075999855995178},{"id":"https://openalex.org/C2776730729","wikidata":"https://www.wikidata.org/wiki/Q1392130","display_name":"Flag (linear algebra)","level":3,"score":0.396699994802475},{"id":"https://openalex.org/C175551986","wikidata":"https://www.wikidata.org/wiki/Q47089","display_name":"Fault (geology)","level":2,"score":0.3772999942302704},{"id":"https://openalex.org/C20277647","wikidata":"https://www.wikidata.org/wiki/Q5227234","display_name":"Data access layer","level":3,"score":0.3698999881744385},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.36329999566078186},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.30649998784065247},{"id":"https://openalex.org/C190793597","wikidata":"https://www.wikidata.org/wiki/Q189768","display_name":"Application layer","level":3,"score":0.30379998683929443},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.2793000042438507},{"id":"https://openalex.org/C152745839","wikidata":"https://www.wikidata.org/wiki/Q5438153","display_name":"Fault detection and isolation","level":3,"score":0.26899999380111694},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.2678000032901764}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.5281/zenodo.23940768","doi":"https://doi.org/10.5281/zenodo.23940768","is_oa":true,"landing_page_url":"https://doi.org/10.5281/zenodo.23940768","pdf_url":null,"source":{"id":"https://openalex.org/S4306400562","display_name":"Zenodo (CERN European Organization for Nuclear Research)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I67311998","host_organization_name":"European Organization for Nuclear Research","host_organization_lineage":["https://openalex.org/I67311998"],"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"},{"id":"doi:10.5281/zenodo.23940769","doi":"https://doi.org/10.5281/zenodo.23940769","is_oa":true,"landing_page_url":"https://doi.org/10.5281/zenodo.23940769","pdf_url":null,"source":{"id":"https://openalex.org/S4306400562","display_name":"Zenodo (CERN European Organization for Nuclear Research)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I67311998","host_organization_name":"European Organization for Nuclear Research","host_organization_lineage":["https://openalex.org/I67311998"],"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":"doi:10.5281/zenodo.23940768","doi":"https://doi.org/10.5281/zenodo.23940768","is_oa":true,"landing_page_url":"https://doi.org/10.5281/zenodo.23940768","pdf_url":null,"source":{"id":"https://openalex.org/S4306400562","display_name":"Zenodo (CERN European Organization for Nuclear Research)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I67311998","host_organization_name":"European Organization for Nuclear Research","host_organization_lineage":["https://openalex.org/I67311998"],"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"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Semantic":[0],"layers":[1],"improve":[2],"text-to-SQL":[3],"accuracy":[4,67,86],"when":[5],"their":[6],"business":[7,144],"definitions":[8],"are":[9],"correct.":[10],"We":[11],"study":[12],"24":[13],"controlled":[14],"faults":[15,76,99],"in":[16,79,102,108],"an":[17,148],"Apache":[18],"Ossie":[19],"model":[20],"over":[21],"TPC-DS,":[22],"covering":[23],"formulas,":[24],"filters,":[25],"synonyms,":[26],"fiscal":[27],"calendars,":[28],"join":[29],"keys":[30],"and":[31,45,83,119,132,174],"value":[32],"mappings.":[33],"Each":[34],"fault":[35],"has":[36],"a":[37,46,63,113],"coherent":[38],"form,":[39,48],"whose":[40,49],"documentation":[41,50],"agrees":[42],"with":[43,60,162],"it,":[44],"contradictory":[47],"retains":[51],"the":[52,116,136,163],"reference":[53,151],"definition.":[54],"In":[55],"1,512":[56],"single-turn,":[57],"tool-free":[58],"trials":[59,82,105],"three":[61],"models,":[62],"correct":[64,137],"layer":[65,90,138,172],"raised":[66,112,133],"from":[68],"60\u201371%":[69],"to":[70,88,152],"100%":[71],"on":[72,135],"this":[73],"benchmark.":[74],"Coherent":[75],"were":[77,100],"followed":[78,107],"46\u201373%":[80],"of":[81,104,156,166],"reduced":[84],"pooled":[85],"relative":[87],"no":[89],"by":[91,139],"26":[92],"percentage":[93,141],"points":[94],"(95%":[95],"CI,":[96],"9\u201343).":[97],"Contradictory":[98],"located":[101,177],"92\u2013100%":[103],"but":[106],"4\u201333%.":[109],"Some":[110],"responses":[111],"concern":[114],"about":[115],"faulted":[117],"definition":[118],"still":[120],"used":[121],"it.":[122],"A":[123],"generic":[124],"audit":[125],"instruction":[126],"did":[127],"not":[128],"reliably":[129],"reduce":[130],"following":[131],"concerns":[134,159,173],"17":[140],"points.":[142],"Plausible":[143],"conventions":[145],"may":[146],"require":[147],"independent":[149],"policy":[150],"verify.":[153],"Author":[154],"annotations":[155],"417":[157],"sampled":[158],"gave":[160],"agreement":[161],"detection":[164],"rule":[165],"Cohen\u2019s":[167],"\u03ba":[168],"=":[169],"0.89":[170],"for":[171,176],"0.90":[175],"faults.":[178]},"counts_by_year":[],"updated_date":"2026-11-05T12:25:35.769452","created_date":"2026-11-05T00:00:00"}