{"id":"https://openalex.org/W7065920544","doi":null,"title":"Fr\u00e5n ord till SQL : Optimering av text-till-SQL-generering i stora spr\u00e5kmodeller","display_name":"Fr\u00e5n ord till SQL : Optimering av text-till-SQL-generering i stora spr\u00e5kmodeller","publication_year":2024,"publication_date":"2024-01-01","ids":{"openalex":"https://openalex.org/W7065920544"},"language":"en","primary_location":{"id":"pmh:oai:DiVA.org:liu-200605","doi":null,"is_oa":true,"landing_page_url":"http://urn.kb.se/resolve?urn=urn:nbn:se:liu:diva-200605","pdf_url":"https://liu.diva-portal.org/smash/get/diva2:1833681/FULLTEXT02","source":{"id":"https://openalex.org/S4306400838","display_name":"DiVA (Linkoping University)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I102134673","host_organization_name":"Link\u00f6ping University","host_organization_lineage":["https://openalex.org/I102134673"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"info:eu-repo/semantics/bachelorThesis"},"volume":null,"type":"dissertation","is_traditional":true,"indexed_in":[],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://liu.diva-portal.org/smash/get/diva2:1833681/FULLTEXT02","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5064350910","display_name":"Niklas Wretblad","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wretblad, Niklas","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":null,"display_name":"Gordh Riseby, Fredrik","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Gordh Riseby, Fredrik","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":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":true,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.5776000022888184,"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":0.5776000022888184,"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":0.3127000033855438,"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":0.031099999323487282,"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":0.9760000109672546},{"id":"https://openalex.org/keywords/large-language-models","display_name":"large language models","score":0.7960000038146973},{"id":"https://openalex.org/keywords/benchmark-reliability","display_name":"benchmark reliability","score":0.6539999842643738},{"id":"https://openalex.org/keywords/query-correction","display_name":"query correction","score":0.5580000281333923},{"id":"https://openalex.org/keywords/zero-shot-prompting","display_name":"zero-shot prompting","score":0.5960000157356262},{"id":"https://openalex.org/keywords/financial-domain","display_name":"financial domain","score":0.335999995470047},{"id":"https://openalex.org/keywords/data-annotation","display_name":"data annotation","score":0.5049999952316284},{"id":"https://openalex.org/keywords/natural-language-to-sql","display_name":"natural language to SQL translation","score":0.42800000309944153}],"concepts":[{"id":"https://openalex.org/C510870499","wikidata":"https://www.wikidata.org/wiki/Q47607","display_name":"SQL","level":2,"score":0.7968000173568726},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7472000122070312},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.6834999918937683},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.5396999716758728},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.453000009059906},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.4440000057220459},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.4230000078678131},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.4203999936580658},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.3885999917984009},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.385699987411499},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3643999993801117},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3528999984264374},{"id":"https://openalex.org/C204323151","wikidata":"https://www.wikidata.org/wiki/Q905424","display_name":"Range (aeronautics)","level":2,"score":0.34389999508857727},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.3158999979496002},{"id":"https://openalex.org/C81669768","wikidata":"https://www.wikidata.org/wiki/Q2359161","display_name":"Precision and recall","level":2,"score":0.3102000057697296},{"id":"https://openalex.org/C67186912","wikidata":"https://www.wikidata.org/wiki/Q367664","display_name":"Data modeling","level":2,"score":0.2818000018596649},{"id":"https://openalex.org/C100675267","wikidata":"https://www.wikidata.org/wiki/Q1371624","display_name":"Background noise","level":2,"score":0.2732999920845032},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.25609999895095825},{"id":"https://openalex.org/C40993552","wikidata":"https://www.wikidata.org/wiki/Q514654","display_name":"Gold standard (test)","level":2,"score":0.25429999828338623}],"mesh":[],"locations_count":1,"locations":[{"id":"pmh:oai:DiVA.org:liu-200605","doi":null,"is_oa":true,"landing_page_url":"http://urn.kb.se/resolve?urn=urn:nbn:se:liu:diva-200605","pdf_url":"https://liu.diva-portal.org/smash/get/diva2:1833681/FULLTEXT02","source":{"id":"https://openalex.org/S4306400838","display_name":"DiVA (Linkoping University)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I102134673","host_organization_name":"Link\u00f6ping University","host_organization_lineage":["https://openalex.org/I102134673"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"info:eu-repo/semantics/bachelorThesis"}],"best_oa_location":{"id":"pmh:oai:DiVA.org:liu-200605","doi":null,"is_oa":true,"landing_page_url":"http://urn.kb.se/resolve?urn=urn:nbn:se:liu:diva-200605","pdf_url":"https://liu.diva-portal.org/smash/get/diva2:1833681/FULLTEXT02","source":{"id":"https://openalex.org/S4306400838","display_name":"DiVA (Linkoping University)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I102134673","host_organization_name":"Link\u00f6ping University","host_organization_lineage":["https://openalex.org/I102134673"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"info:eu-repo/semantics/bachelorThesis"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320322225","display_name":"Link\u00f6pings Universitet","ror":"https://ror.org/05ynxx418"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7065920544.pdf","grobid_xml":"https://content.openalex.org/works/W7065920544.grobid-xml"},"referenced_works_count":36,"referenced_works":["https://openalex.org/W46659105","https://openalex.org/W2012056301","https://openalex.org/W2041191762","https://openalex.org/W2157331557","https://openalex.org/W2165467455","https://openalex.org/W2270062199","https://openalex.org/W2751448157","https://openalex.org/W2937423263","https://openalex.org/W2963341956","https://openalex.org/W2969958763","https://openalex.org/W3095319910","https://openalex.org/W3119997354","https://openalex.org/W3156470785","https://openalex.org/W3175818566","https://openalex.org/W3177813494","https://openalex.org/W3185341429","https://openalex.org/W3201174429","https://openalex.org/W3203321135","https://openalex.org/W3210904070","https://openalex.org/W4309674289","https://openalex.org/W4313384047","https://openalex.org/W4327810158","https://openalex.org/W4360836968","https://openalex.org/W4360891289","https://openalex.org/W4367672983","https://openalex.org/W4384615768","https://openalex.org/W4390513007","https://openalex.org/W4392681182","https://openalex.org/W4396571402","https://openalex.org/W4396665924","https://openalex.org/W4396762144","https://openalex.org/W4404594861","https://openalex.org/W7133214447","https://openalex.org/W7133222210","https://openalex.org/W7133230376","https://openalex.org/W7155906632"],"related_works":["https://openalex.org/W4402671227","https://openalex.org/W7134954916","https://openalex.org/W4403836156","https://openalex.org/W4410234067","https://openalex.org/W7223236989","https://openalex.org/W4393242029","https://openalex.org/W4416036962","https://openalex.org/W4379258895","https://openalex.org/W4416323728","https://openalex.org/W4416075866"],"abstract_inverted_index":{"Text-to-SQL,":[0],"which":[1,147],"involves":[2],"translating":[3],"natural":[4,188],"language":[5,189],"into":[6,199],"Structured":[7],"Query":[8],"Language":[9],"(SQL),":[10],"is":[11,29],"crucial":[12,278],"for":[13,26,243,255,262],"enabling":[14],"broad":[15],"access":[16],"to":[17,32,77,88,192,203,229,279],"structured":[18],"databases":[19],"without":[20],"expert":[21],"knowledge.":[22],"However,":[23],"designing":[24],"models":[25,164,201],"such":[27,40],"tasks":[28],"challenging":[30],"due":[31],"numerous":[33],"factors,":[34],"including":[35],"the":[36,54,61,67,94,116,120,127,131,158,172,182,194,220,236,239,260],"presence":[37,132,141],"of":[38,53,58,69,119,126,133,142,174,184,196,222,241,289],"\u2019noise,\u2019":[39],"as":[41,138],"ambiguous":[42],"questions":[43,95,108,198],"and":[44,56,66,80,91,96,109,122,202,212,232,274],"syntactical":[45],"errors.":[46],"This":[47,249],"thesis":[48,179,237],"provides":[49],"an":[50],"in-depth":[51],"analysis":[52,125],"distribution":[55],"types":[57,288],"noise":[59,70,90,106,134,186,205,272],"in":[60,93,107,115,135,187,206,264],"widely":[62],"used":[63],"BIRD-Bench":[64,74],"benchmark":[65],"impact":[68,156],"on":[71,157,165,214],"models.":[72],"While":[73],"was":[75,85],"created":[76,87],"model":[78],"dirty":[79],"noisy":[81,197],"database":[82],"values,":[83],"it":[84],"not":[86],"contain":[89],"errors":[92],"gold":[97,110,144,151],"queries.":[98,248],"We":[99,268],"found":[100],"after":[101],"a":[102,123,154,215,251],"manual":[103],"evaluation":[104],"that":[105,270,284],"queries":[111],"are":[112,277],"highly":[113],"prevalent":[114],"financial":[117],"domain":[118],"dataset,":[121],"further":[124],"other":[128,136],"domains":[129],"indicate":[130],"parts":[137],"well.":[139],"The":[140,178],"incorrect":[143,150],"SQL":[145,167,247],"queries,":[146,168],"then":[148,180],"generate":[149],"answers,":[152],"has":[153],"significant":[155],"benchmark\u2019s":[159],"reliability.":[160],"Surprisingly,":[161],"when":[162],"evaluating":[163],"corrected":[166],"zero-shot":[169],"baselines":[170],"surpassed":[171],"performance":[173],"state-of-the-art":[175],"prompting":[176],"methods.":[177],"introduces":[181],"concept":[183],"classifying":[185],"questions,":[190],"aiming":[191],"prevent":[193],"entry":[195],"text-to-SQL":[200],"annotate":[204],"existing":[207],"datasets.":[208],"Experiments":[209],"using":[210],"GPT-3.5":[211],"GPT-4":[213],"manually":[216],"annotated":[217],"dataset":[218,266],"demonstrated":[219],"viability":[221],"this":[223],"approach,":[224],"with":[225],"classifiers":[226],"achieving":[227],"up":[228],"0.81":[230],"recall":[231],"80%":[233],"accuracy.":[234],"Additionally,":[235],"explored":[238],"use":[240],"LLMs":[242,263],"automatically":[244],"correcting":[245],"faulty":[246],"showed":[250],"100%":[252],"success":[253],"rate":[254],"specific":[256],"query":[257],"corrections,":[258],"highlighting":[259],"potential":[261],"improving":[265],"quality.":[267],"conclude":[269],"informative":[271],"labels":[273],"reliable":[275],"benchmarks":[276],"developing":[280],"new":[281],"Text-to-SQL":[282],"methods":[283],"can":[285],"handle":[286],"varying":[287],"noise.":[290]},"counts_by_year":[],"updated_date":"2026-11-07T11:25:07.637180","created_date":"2025-10-10T00:00:00"}