{"id":"https://openalex.org/W7164137353","doi":"https://doi.org/10.48550/arxiv.2606.10125","title":"Robust Active Learning for Few-Shot Example Selection in Text-to-SQL","display_name":"Robust Active Learning for Few-Shot Example Selection in Text-to-SQL","publication_year":2026,"publication_date":"2026-06-08","ids":{"openalex":"https://openalex.org/W7164137353","doi":"https://doi.org/10.48550/arxiv.2606.10125"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2606.10125","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2606.10125","pdf_url":"https://arxiv.org/pdf/2606.10125","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":"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/2606.10125","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5044056393","display_name":"Arash Pourhabib","orcid":"https://orcid.org/0000-0002-9394-8196","observed_orcids":["https://orcid.org/0000-0002-9394-8196"]},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Pourhabib, Arash","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":["https://openalex.org/A5044056393"],"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/T12072","display_name":"Machine Learning and Algorithms","score":0.6826000213623047,"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/T12072","display_name":"Machine Learning and Algorithms","score":0.6826000213623047,"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":0.06459999829530716,"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/T10317","display_name":"Advanced Database Systems and Queries","score":0.039500001817941666,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/text-to-sql","display_name":"text-to-SQL","score":0.9490000009536743},{"id":"https://openalex.org/keywords/active-learning-machine-learning","display_name":"active learning (machine learning)","score":0.8960000276565552},{"id":"https://openalex.org/keywords/submodular-optimization","display_name":"submodular optimization","score":0.6949999928474426},{"id":"https://openalex.org/keywords/noisy-annotations","display_name":"noisy annotations","score":0.7540000081062317},{"id":"https://openalex.org/keywords/query-embedding","display_name":"query embedding","score":0.6209999918937683},{"id":"https://openalex.org/keywords/retrieval-models","display_name":"retrieval models","score":0.4309999942779541},{"id":"https://openalex.org/keywords/cross-domain-retrieval","display_name":"cross-domain retrieval","score":0.5839999914169312},{"id":"https://openalex.org/keywords/approximation-guarantees","display_name":"approximation guarantees","score":0.46799999475479126}],"concepts":[{"id":"https://openalex.org/C178621042","wikidata":"https://www.wikidata.org/wiki/Q7631710","display_name":"Submodular set function","level":2,"score":0.7208999991416931},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.57669997215271},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.5467000007629395},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4722000062465668},{"id":"https://openalex.org/C77967617","wikidata":"https://www.wikidata.org/wiki/Q4677561","display_name":"Active learning (machine learning)","level":2,"score":0.4528000056743622},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.44769999384880066},{"id":"https://openalex.org/C81917197","wikidata":"https://www.wikidata.org/wiki/Q628760","display_name":"Selection (genetic algorithm)","level":2,"score":0.4429999887943268},{"id":"https://openalex.org/C55166926","wikidata":"https://www.wikidata.org/wiki/Q2892946","display_name":"Oracle","level":2,"score":0.38519999384880066},{"id":"https://openalex.org/C51823790","wikidata":"https://www.wikidata.org/wiki/Q504353","display_name":"Greedy algorithm","level":2,"score":0.3781000077724457},{"id":"https://openalex.org/C74193536","wikidata":"https://www.wikidata.org/wiki/Q574844","display_name":"Kernel (algebra)","level":2,"score":0.3765999972820282},{"id":"https://openalex.org/C77553402","wikidata":"https://www.wikidata.org/wiki/Q13222579","display_name":"Upper and lower bounds","level":2,"score":0.36820000410079956},{"id":"https://openalex.org/C106286213","wikidata":"https://www.wikidata.org/wiki/Q898572","display_name":"Matroid","level":2,"score":0.3630000054836273},{"id":"https://openalex.org/C152139883","wikidata":"https://www.wikidata.org/wiki/Q252973","display_name":"Mutual information","level":2,"score":0.36149999499320984},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.3431999981403351},{"id":"https://openalex.org/C43214815","wikidata":"https://www.wikidata.org/wiki/Q7310987","display_name":"Reliability (semiconductor)","level":3,"score":0.34299999475479126},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.33889999985694885},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.3345000147819519},{"id":"https://openalex.org/C2776321320","wikidata":"https://www.wikidata.org/wiki/Q857525","display_name":"Annotation","level":2,"score":0.3336000144481659},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.32109999656677246},{"id":"https://openalex.org/C178650346","wikidata":"https://www.wikidata.org/wiki/Q201984","display_name":"Covariance","level":2,"score":0.31859999895095825},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.3084999918937683},{"id":"https://openalex.org/C173801870","wikidata":"https://www.wikidata.org/wiki/Q201413","display_name":"Heuristic","level":2,"score":0.29589998722076416},{"id":"https://openalex.org/C164660894","wikidata":"https://www.wikidata.org/wiki/Q2037833","display_name":"Piecewise","level":2,"score":0.2883000075817108},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.2809999883174896},{"id":"https://openalex.org/C93959086","wikidata":"https://www.wikidata.org/wiki/Q6888345","display_name":"Model selection","level":2,"score":0.27469998598098755},{"id":"https://openalex.org/C151876577","wikidata":"https://www.wikidata.org/wiki/Q7049464","display_name":"Nonlinear dimensionality reduction","level":3,"score":0.27070000767707825},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.25850000977516174},{"id":"https://openalex.org/C2778572836","wikidata":"https://www.wikidata.org/wiki/Q380933","display_name":"Space (punctuation)","level":2,"score":0.2549000084400177}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2606.10125","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2606.10125","pdf_url":"https://arxiv.org/pdf/2606.10125","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":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2606.10125","doi":"https://doi.org/10.48550/arxiv.2606.10125","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2606.10125","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:2606.10125","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2606.10125","pdf_url":"https://arxiv.org/pdf/2606.10125","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":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320309480","display_name":"Nvidia","ror":"https://ror.org/03jdj4y14"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7164137353.pdf","grobid_xml":"https://content.openalex.org/works/W7164137353.grobid-xml"},"referenced_works_count":1,"referenced_works":["https://openalex.org/W2889326414"],"related_works":["https://openalex.org/W4389519605","https://openalex.org/W7128404486","https://openalex.org/W4389523899","https://openalex.org/W4416339404","https://openalex.org/W4280590278","https://openalex.org/W3199077625","https://openalex.org/W4377864495","https://openalex.org/W4381326864","https://openalex.org/W7214057616","https://openalex.org/W7131273953"],"abstract_inverted_index":{"Domain-specific":[0],"text-to-SQL":[1],"systems":[2],"ground":[3],"a":[4,43,60,66,87,135,224],"large":[5,116],"language":[6],"model":[7,137],"by":[8,100,144],"retrieving":[9],"annotated":[10],"few-shot":[11,140],"examples,":[12],"and":[13,53,77,112,150,153,167,178,184,194,229],"each":[14,209],"example":[15,244],"needs":[16],"expert-written":[17],"SQL.":[18],"We":[19,58,70],"treat":[20],"the":[21,33,73,91,97,118,126,130,169,172,188,199,203,212,216,230,250],"choice":[22],"of":[23,36],"which":[24],"queries":[25],"to":[26,120,129,241],"annotate":[27,242],"as":[28],"constrained":[29],"experimental":[30,110],"design":[31,127],"on":[32,108,159,168],"low-dimensional":[34],"manifold":[35],"query":[37],"embeddings,":[38],"with":[39],"query-dependent":[40,80],"annotation":[41,190],"noise,":[42,81,149],"partition":[44,92,204],"matroid":[45],"constraint":[46],"that":[47,64,72,138,198],"spreads":[48],"selections":[49],"across":[50],"semantic":[51],"domains,":[52],"an":[54,101,163],"unknown":[55],"covariance":[56],"structure.":[57],"propose":[59],"stratified":[61,83],"greedy":[62,84],"algorithm":[63],"maximizes":[65],"heteroscedastic":[67],"information-gain":[68],"objective.":[69],"prove":[71],"objective":[74,128],"is":[75,240],"monotone":[76],"submodular":[78],"under":[79,90],"so":[82],"selection":[85,186,220],"carries":[86],"1/2-approximation":[88],"guarantee":[89,98],"constraint.":[93],"Under":[94],"kernel":[95],"misspecification":[96],"degrades":[99],"additive":[102],"spectral":[103],"term;":[104],"we":[105,133,154],"compute":[106],"it":[107,114],"both":[109,160],"pools":[111],"find":[113],"too":[115],"for":[117],"bound":[119],"be":[121],"quantitatively":[122],"informative.":[123],"To":[124],"connect":[125],"downstream":[131],"task,":[132],"give":[134],"retrieval":[136,177],"bounds":[139],"accuracy":[141],"from":[142,202,249],"below":[143],"per-domain":[145],"fill":[146],"distance,":[147],"demonstration":[148],"domain":[151,246],"coverage,":[152],"calibrate":[155],"its":[156],"locality":[157],"assumption":[158],"pools.":[161],"On":[162],"enterprise":[164],"supply-chain":[165],"corpus":[166],"BIRD":[170],"benchmark,":[171],"selected":[173],"banks":[174],"improve":[175],"cross-domain":[176],"end-to-end":[179],"LLM":[180],"SQL":[181],"over":[182],"random":[183],"distance-based":[185],"at":[187,226],"same":[189],"budget.":[191],"Stratified":[192],"controls":[193],"pre-specified":[195],"tests":[196],"show":[197],"gain":[200],"comes":[201],"constraint:":[205],"uniform":[206],"sampling":[207],"within":[208,221],"stratum":[210],"matches":[211],"full":[213],"method":[214],"in":[215],"oracle-label":[217],"evaluations,":[218],"farthest-point":[219],"strata":[222],"adds":[223],"little":[225],"small":[227],"budgets,":[228],"noise":[231],"weighting":[232],"has":[233],"no":[234],"measurable":[235],"effect.":[236],"The":[237],"practical":[238],"advice":[239],"one":[243],"per":[245,247],"batch":[248,252],"first":[251],"on.":[253]},"counts_by_year":[],"updated_date":"2026-11-08T12:12:28.789561","created_date":"2026-06-11T00:00:00"}