{"id":"https://openalex.org/W7225266673","doi":"https://doi.org/10.48550/arxiv.2611.04318","title":"Text-to-SQL Models Make Choices Without Saying So","display_name":"Text-to-SQL Models Make Choices Without Saying So","publication_year":2026,"publication_date":"2026-11-03","ids":{"openalex":"https://openalex.org/W7225266673","doi":"https://doi.org/10.48550/arxiv.2611.04318"},"language":"en","primary_location":{"id":"doi:10.48550/arxiv.2611.04318","doi":"https://doi.org/10.48550/arxiv.2611.04318","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2611.04318","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":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"},"volume":null,"type":"preprint","is_traditional":true,"indexed_in":["datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://doi.org/10.48550/arxiv.2611.04318","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5160692596","display_name":"Yichen Xu","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xu, Yichen","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5152047360","display_name":"\u4ed5\u6c9b \u6797","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Lin, Shipei","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5160590947","display_name":"Chenhao Ma","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ma, Chenhao","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"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":0.3783999979496002,"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":0.3783999979496002,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.2856000065803528,"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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.046300001442432404,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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/text-to-sql","display_name":"text-to-SQL","score":0.996999979019165},{"id":"https://openalex.org/keywords/ambiguous-questions","display_name":"ambiguous questions","score":0.3619999885559082},{"id":"https://openalex.org/keywords/database-query-generation","display_name":"database query generation","score":0.3580000102519989},{"id":"https://openalex.org/keywords/language-model-evaluation","display_name":"language model evaluation","score":0.3840000033378601},{"id":"https://openalex.org/keywords/benchmarking","display_name":"benchmarking","score":0.5049999952316284},{"id":"https://openalex.org/keywords/bird-benchmark","display_name":"BIRD benchmark","score":0.5950000286102295}],"concepts":[{"id":"https://openalex.org/C527412718","wikidata":"https://www.wikidata.org/wiki/Q855395","display_name":"Interpretation (philosophy)","level":2,"score":0.7678999900817871},{"id":"https://openalex.org/C176730311","wikidata":"https://www.wikidata.org/wiki/Q867668","display_name":"Multiple choice","level":3,"score":0.5590000152587891},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5569999814033508},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.5065000057220459},{"id":"https://openalex.org/C135598885","wikidata":"https://www.wikidata.org/wiki/Q1366302","display_name":"Row","level":2,"score":0.42399999499320984},{"id":"https://openalex.org/C144237770","wikidata":"https://www.wikidata.org/wiki/Q747534","display_name":"Mathematical economics","level":1,"score":0.34049999713897705},{"id":"https://openalex.org/C2777267654","wikidata":"https://www.wikidata.org/wiki/Q3519023","display_name":"Test (biology)","level":2,"score":0.34049999713897705},{"id":"https://openalex.org/C2777152325","wikidata":"https://www.wikidata.org/wiki/Q108163","display_name":"Proposition","level":2,"score":0.3346000015735626},{"id":"https://openalex.org/C2778348673","wikidata":"https://www.wikidata.org/wiki/Q739302","display_name":"Production (economics)","level":2,"score":0.3068000078201294},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.2872999906539917},{"id":"https://openalex.org/C149782125","wikidata":"https://www.wikidata.org/wiki/Q160039","display_name":"Econometrics","level":1,"score":0.25360000133514404}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2611.04318","doi":"https://doi.org/10.48550/arxiv.2611.04318","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2611.04318","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":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"doi:10.48550/arxiv.2611.04318","doi":"https://doi.org/10.48550/arxiv.2611.04318","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2611.04318","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":null,"license_id":null,"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":["https://openalex.org/W7168274383","https://openalex.org/W7171536026","https://openalex.org/W7203441219","https://openalex.org/W3093562467","https://openalex.org/W7203648765","https://openalex.org/W7078726768","https://openalex.org/W7133356581","https://openalex.org/W4385571778","https://openalex.org/W7169563875","https://openalex.org/W7220356223"],"abstract_inverted_index":{"A":[0],"text-to-SQL":[1],"answer":[2,92,249],"can":[3,20,194],"run,":[4],"return":[5,132],"a":[6,26,58,68,166,192,198,205,208,268],"plausible":[7],"number":[8],"and":[9,39,85,89,100,222],"still":[10],"compute":[11,120],"something":[12],"other":[13,184],"than":[14,266],"what":[15],"the":[16,23,40,82,101,129,138,146,159,169,176,183,187,234,247],"analyst":[17],"meant.":[18],"This":[19],"happen":[21],"when":[22,123],"request":[24,131,206],"leaves":[25,207],"calculation":[27],"choice":[28,69,83,167,209],"open,":[29,210],"such":[30,67,165],"as":[31],"whether":[32,204],"to":[33],"count":[34],"rows":[35],"or":[36],"distinct":[37],"entities,":[38],"model":[41],"settles":[42],"it":[43,72,74,196,201],"without":[44,144,197,254],"saying":[45],"so.":[46],"Standard":[47],"benchmarks":[48],"cannot":[49],"detect":[50],"this,":[51],"because":[52],"they":[53,141],"score":[54],"each":[55,91,121,213],"question":[56],"against":[57],"single":[59,248],"reference":[60],"interpretation.":[61,185],"We":[62],"introduce":[63],"SpecBridge,":[64],"which":[65],"tests":[66,139,221],"by":[70,93,243],"varying":[71],"alone:":[73],"poses":[75],"three":[76],"otherwise":[77],"identical":[78],"requests,":[79],"one":[80,86],"leaving":[81],"open":[84,130,237],"per":[87],"interpretation,":[88],"scores":[90],"running":[94],"it.":[95],"The":[96,148],"databases":[97],"are":[98,103,180],"real,":[99],"choices":[102],"ones":[104],"that":[105,239,250],"made":[106],"models":[107,118],"fail":[108],"on":[109,161,223,257],"existing":[110,226],"benchmarks.":[111],"On":[112,219],"204":[113],"hand-validated":[114],"tests,":[115],"four":[116],"language":[117],"usually":[119],"interpretation":[122,214,242],"asked":[124],"for":[125,128],"it,":[126],"yet":[127],"both":[133],"in":[134,151,154,173,190,215],"only":[135],"15-58%":[136],"of":[137,175,228,236],"where":[140,164],"can,":[142],"often":[143],"mentioning":[145],"choice.":[147],"gap":[149,188],"lies":[150,189],"reporting,":[152,191],"not":[153],"computing.":[155],"Benchmarks":[156],"even":[157],"penalize":[158],"alternative:":[160],"BIRD":[162],"questions":[163],"changes":[168],"answer,":[170],"over":[171,246],"two":[172],"five":[174],"answers":[177,212],"marked":[178],"wrong":[179],"right":[181],"under":[182],"Because":[186],"system":[193],"narrow":[195],"stronger":[199],"model:":[200],"first":[202],"decides":[203],"then":[211],"its":[216],"own":[217],"call.":[218],"our":[220],"AMBROSIA,":[224],"an":[225],"benchmark":[227],"ambiguous":[229],"questions,":[230],"this":[231],"approach":[232],"raises":[233],"share":[235],"requests":[238],"get":[240],"every":[241],"29-63":[244],"points":[245],"production":[251],"assistants":[252],"give,":[253],"lowering":[255],"precision":[256],"clear":[258],"requests.":[259],"It":[260],"also":[261],"needs":[262],"fewer":[263],"user":[264],"turns":[265],"asking":[267],"clarifying":[269],"question.":[270]},"counts_by_year":[],"updated_date":"2026-11-06T12:05:46.655746","created_date":"2026-11-05T00:00:00"}