{"id":"https://openalex.org/W4411450116","doi":"https://doi.org/10.1145/3729376","title":"Automated Trustworthiness Oracle Generation for Machine Learning Text Classifiers","display_name":"Automated Trustworthiness Oracle Generation for Machine Learning Text Classifiers","publication_year":2025,"publication_date":"2025-06-19","ids":{"openalex":"https://openalex.org/W4411450116","doi":"https://doi.org/10.1145/3729376"},"language":"en","primary_location":{"id":"doi:10.1145/3729376","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3729376","pdf_url":null,"source":{"id":"https://openalex.org/S4404663975","display_name":"Proceedings of the ACM on software engineering.","issn_l":"2994-970X","issn":["2994-970X"],"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":"cc-by-sa","license_id":"https://openalex.org/licenses/cc-by-sa","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the ACM on Software Engineering","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://doi.org/10.1145/3729376","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5118393622","display_name":"Lam Nguyen Tung","orcid":null},"institutions":[{"id":"https://openalex.org/I56590836","display_name":"Monash University","ror":"https://ror.org/02bfwt286","country_code":"AU","type":"education","lineage":["https://openalex.org/I56590836"]}],"countries":["AU"],"is_corresponding":true,"raw_author_name":"Lam Nguyen Tung","raw_affiliation_strings":["Monash University, Melbourne, Australia"],"raw_orcid":"https://orcid.org/0009-0000-3038-8403","affiliations":[{"raw_affiliation_string":"Monash University, Melbourne, Australia","institution_ids":["https://openalex.org/I56590836"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5111712860","display_name":"S. B. Cho","orcid":null},"institutions":[{"id":"https://openalex.org/I154130895","display_name":"University of Auckland","ror":"https://ror.org/03b94tp07","country_code":"NZ","type":"education","lineage":["https://openalex.org/I154130895"]}],"countries":["NZ"],"is_corresponding":false,"raw_author_name":"Steven Cho","raw_affiliation_strings":["University of Auckland, Auckland, New Zealand"],"raw_orcid":"https://orcid.org/0009-0001-2548-4406","affiliations":[{"raw_affiliation_string":"University of Auckland, Auckland, New Zealand","institution_ids":["https://openalex.org/I154130895"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102717874","display_name":"Xiaoning Du","orcid":null},"institutions":[{"id":"https://openalex.org/I56590836","display_name":"Monash University","ror":"https://ror.org/02bfwt286","country_code":"AU","type":"education","lineage":["https://openalex.org/I56590836"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Xiaoning Du","raw_affiliation_strings":["Monash University, Melbourne, Australia"],"raw_orcid":"https://orcid.org/0000-0003-3728-9541","affiliations":[{"raw_affiliation_string":"Monash University, Melbourne, Australia","institution_ids":["https://openalex.org/I56590836"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5065637872","display_name":"Neelofar Neelofar","orcid":"https://orcid.org/0000-0003-2572-0250"},"institutions":[{"id":"https://openalex.org/I1320473756","display_name":"The Royal Melbourne Hospital","ror":"https://ror.org/005bvs909","country_code":"AU","type":"funder","lineage":["https://openalex.org/I1320473756","https://openalex.org/I4210158168"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Neelofar Neelofar","raw_affiliation_strings":["Royal Melbourne Institute of Technology, Melbourne, Australia"],"raw_orcid":"https://orcid.org/0000-0003-2572-0250","affiliations":[{"raw_affiliation_string":"Royal Melbourne Institute of Technology, Melbourne, Australia","institution_ids":["https://openalex.org/I1320473756"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5068101658","display_name":"Valerio Terragni","orcid":"https://orcid.org/0000-0001-5885-9297"},"institutions":[{"id":"https://openalex.org/I154130895","display_name":"University of Auckland","ror":"https://ror.org/03b94tp07","country_code":"NZ","type":"education","lineage":["https://openalex.org/I154130895"]}],"countries":["NZ"],"is_corresponding":false,"raw_author_name":"Valerio Terragni","raw_affiliation_strings":["University of Auckland, Auckland, New Zealand"],"raw_orcid":"https://orcid.org/0000-0001-5885-9297","affiliations":[{"raw_affiliation_string":"University of Auckland, Auckland, New Zealand","institution_ids":["https://openalex.org/I154130895"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5011541744","display_name":"Stefano Ruberto","orcid":"https://orcid.org/0000-0001-8666-2782"},"institutions":[{"id":"https://openalex.org/I4210118689","display_name":"Joint Research Centre","ror":"https://ror.org/02qezmz13","country_code":"IT","type":"government","lineage":["https://openalex.org/I1320481043","https://openalex.org/I2800387288","https://openalex.org/I4210118689","https://openalex.org/I4210161702"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Stefano Ruberto","raw_affiliation_strings":["Joint Research Centre at the European Commission, Ispra, Italy"],"raw_orcid":"https://orcid.org/0000-0001-8666-2782","affiliations":[{"raw_affiliation_string":"Joint Research Centre at the European Commission, Ispra, Italy","institution_ids":["https://openalex.org/I4210118689"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5035346540","display_name":"Aldeida Aleti","orcid":"https://orcid.org/0000-0002-1716-690X"},"institutions":[{"id":"https://openalex.org/I56590836","display_name":"Monash University","ror":"https://ror.org/02bfwt286","country_code":"AU","type":"education","lineage":["https://openalex.org/I56590836"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Aldeida Aleti","raw_affiliation_strings":["Monash University, Melbourne, Australia"],"raw_orcid":"https://orcid.org/0000-0002-1716-690X","affiliations":[{"raw_affiliation_string":"Monash University, Melbourne, Australia","institution_ids":["https://openalex.org/I56590836"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":7,"corresponding_author_ids":["https://openalex.org/A5118393622"],"corresponding_institution_ids":["https://openalex.org/I56590836"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.06581506,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"2","issue":"FSE","first_page":"2382","last_page":"2405"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11689","display_name":"Adversarial Robustness in Machine Learning","score":0.9995999932289124,"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/T11689","display_name":"Adversarial Robustness in Machine Learning","score":0.9995999932289124,"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/T12026","display_name":"Explainable Artificial Intelligence (XAI)","score":0.9937000274658203,"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/T10883","display_name":"Ethics and Social Impacts of AI","score":0.9629999995231628,"subfield":{"id":"https://openalex.org/subfields/3311","display_name":"Safety Research"},"field":{"id":"https://openalex.org/fields/33","display_name":"Social Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7955721616744995},{"id":"https://openalex.org/keywords/oracle","display_name":"Oracle","score":0.7337839603424072},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.7038604021072388},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.701191782951355},{"id":"https://openalex.org/keywords/leverage","display_name":"Leverage (statistics)","score":0.5583613514900208},{"id":"https://openalex.org/keywords/spurious-relationship","display_name":"Spurious relationship","score":0.5547277331352234},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.4915710389614105},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.4191061854362488},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.32138803601264954}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7955721616744995},{"id":"https://openalex.org/C55166926","wikidata":"https://www.wikidata.org/wiki/Q2892946","display_name":"Oracle","level":2,"score":0.7337839603424072},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.7038604021072388},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.701191782951355},{"id":"https://openalex.org/C153083717","wikidata":"https://www.wikidata.org/wiki/Q6535263","display_name":"Leverage (statistics)","level":2,"score":0.5583613514900208},{"id":"https://openalex.org/C97256817","wikidata":"https://www.wikidata.org/wiki/Q1462316","display_name":"Spurious relationship","level":2,"score":0.5547277331352234},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.4915710389614105},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4191061854362488},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.32138803601264954},{"id":"https://openalex.org/C115903868","wikidata":"https://www.wikidata.org/wiki/Q80993","display_name":"Software engineering","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3729376","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3729376","pdf_url":null,"source":{"id":"https://openalex.org/S4404663975","display_name":"Proceedings of the ACM on software engineering.","issn_l":"2994-970X","issn":["2994-970X"],"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":"cc-by-sa","license_id":"https://openalex.org/licenses/cc-by-sa","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the ACM on Software Engineering","raw_type":"journal-article"}],"best_oa_location":{"id":"doi:10.1145/3729376","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3729376","pdf_url":null,"source":{"id":"https://openalex.org/S4404663975","display_name":"Proceedings of the ACM on software engineering.","issn_l":"2994-970X","issn":["2994-970X"],"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":"cc-by-sa","license_id":"https://openalex.org/licenses/cc-by-sa","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the ACM on Software Engineering","raw_type":"journal-article"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/16","display_name":"Peace, Justice and strong institutions","score":0.8100000023841858}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":64,"referenced_works":["https://openalex.org/W1932198206","https://openalex.org/W1996796871","https://openalex.org/W2032959067","https://openalex.org/W2041713059","https://openalex.org/W2081580037","https://openalex.org/W2097696338","https://openalex.org/W2126574721","https://openalex.org/W2136930489","https://openalex.org/W2165403938","https://openalex.org/W2167347019","https://openalex.org/W2237502368","https://openalex.org/W2282821441","https://openalex.org/W2406986017","https://openalex.org/W2493916176","https://openalex.org/W2614087582","https://openalex.org/W2616028256","https://openalex.org/W2727431395","https://openalex.org/W2744032385","https://openalex.org/W2804337238","https://openalex.org/W2888824816","https://openalex.org/W2891503716","https://openalex.org/W2921802966","https://openalex.org/W2951165326","https://openalex.org/W2963327228","https://openalex.org/W2967287319","https://openalex.org/W2990138404","https://openalex.org/W2995406462","https://openalex.org/W2999637955","https://openalex.org/W3007157104","https://openalex.org/W3015001695","https://openalex.org/W3016970897","https://openalex.org/W3046849394","https://openalex.org/W3048549109","https://openalex.org/W3087720408","https://openalex.org/W3099331415","https://openalex.org/W3100341617","https://openalex.org/W3103185335","https://openalex.org/W3103751997","https://openalex.org/W3103934428","https://openalex.org/W3104125207","https://openalex.org/W3114442852","https://openalex.org/W3120532656","https://openalex.org/W3130373138","https://openalex.org/W3173380736","https://openalex.org/W3208147779","https://openalex.org/W3208971243","https://openalex.org/W4220891756","https://openalex.org/W4221139076","https://openalex.org/W4224982959","https://openalex.org/W4225150645","https://openalex.org/W4231410305","https://openalex.org/W4240935049","https://openalex.org/W4249127983","https://openalex.org/W4288929760","https://openalex.org/W4306321664","https://openalex.org/W4387966251","https://openalex.org/W4388336299","https://openalex.org/W4390043316","https://openalex.org/W4390490761","https://openalex.org/W4392297945","https://openalex.org/W4399206229","https://openalex.org/W4399647035","https://openalex.org/W4411531990","https://openalex.org/W6892985298"],"related_works":["https://openalex.org/W3113091479","https://openalex.org/W2162899405","https://openalex.org/W941090075","https://openalex.org/W2044987316","https://openalex.org/W3134374554","https://openalex.org/W2237480245","https://openalex.org/W2075065631","https://openalex.org/W2519167559","https://openalex.org/W4311248832","https://openalex.org/W3121164913"],"abstract_inverted_index":{"Machine":[0],"learning":[1],"(ML)":[2],"for":[3,177,291],"text":[4,178,292],"classification":[5],"has":[6,127],"been":[7,128],"widely":[8],"used":[9],"in":[10,61,81,113],"various":[11],"domains,":[12],"such":[13,46,86,303],"as":[14,47,122,304],"toxicity":[15],"detection,":[16],"chatbot":[17],"consulting,":[18],"and":[19,29,50,72,160,210,312,325],"review":[20],"analysis.":[21],"These":[22,64],"applications":[23],"can":[24,92],"significantly":[25],"impact":[26],"ethics,":[27],"economics,":[28],"human":[30,59,261],"behavior,":[31],"raising":[32],"serious":[33],"concerns":[34],"about":[35],"trusting":[36],"ML":[37,62,202],"decisions.":[38],"Several":[39],"studies":[40],"indicate":[41],"that":[42,237,296],"traditional":[43],"uncertainty":[44,301],"metrics,":[45,52,302],"model":[48,254,305],"confidence,":[49,306],"performance":[51,91],"like":[53],"accuracy,":[54],"are":[55,88,106,192,264],"insufficient":[56],"to":[57,102,133,189,195,205],"build":[58],"trust":[60],"models.":[63],"models":[65],"often":[66],"learn":[67],"spurious":[68],"correlations":[69,87],"during":[70,77],"training":[71],"predict":[73],"based":[74,109,145,218,251],"on":[75,110,146,219,253,266,299],"them":[76],"inference.":[78],"When":[79],"deployed":[80],"the":[82,114,123,134,140,147,170,184,187,196,207,216,277,322],"real":[83],"world,":[84],"where":[85],"absent,":[89],"their":[90,212,258],"deteriorate":[93],"significantly.":[94],"To":[95,163,256],"avoid":[96],"this,":[97,118],"a":[98,119,190,223,232,248,286],"common":[99],"practice":[100],"is":[101,157,331],"test":[103],"whether":[104,183],"predictions":[105],"made":[107],"reasonably":[108],"valid":[111],"patterns":[112],"data.":[115],"Along":[116],"with":[117,215,247,260,284,334],"challenge":[120],"known":[121],"trustworthiness":[124,138,173,239],"oracle":[125,174],"problem":[126],"introduced.":[129],"So":[130],"far,":[131],"due":[132],"lack":[135],"of":[136,225,270,279],"automated":[137,172],"oracles,":[139],"assessment":[141],"requires":[142],"manual":[143],"validation,":[144],"decision":[148],"process":[149],"disclosed":[150],"by":[151,242],"explanation":[152,203],"methods.":[153],"However,":[154],"this":[155,165],"approach":[156],"time-consuming,":[158],"error-prone,":[159],"not":[161],"scalable.":[162],"address":[164],"problem,":[166],"we":[167,200,229,275],"propose":[168],"TOKI,":[169],"first":[171],"generation":[175],"method":[176,236,283,290,330],"classifiers.":[179],"TOKI":[180,246,316],"automatically":[181],"checks":[182],"words":[185,209],"contributing":[186],"most":[188],"prediction":[191,300],"semantically":[193],"related":[194],"predicted":[197],"class.":[198],"Specifically,":[199],"leverage":[201],"methods":[204],"extract":[206],"decision-contributing":[208],"measure":[211],"semantic":[213],"relatedness":[214],"class":[217],"word":[220],"embeddings.":[221],"As":[222],"demonstration":[224],"its":[226],"practical":[227],"usefulness,":[228],"also":[230],"introduce":[231],"novel":[233],"adversarial":[234,281,288,328],"attack":[235,282,289,329],"targets":[238],"vulnerabilities":[240],"identified":[241],"TOKI.":[243],"We":[244],"compare":[245,276],"naive":[249,323],"baseline":[250],"solely":[252],"confidence.":[255],"evaluate":[257],"alignment":[259],"judgement,":[262],"experiments":[263],"conducted":[265],"human-created":[267],"ground":[268],"truths":[269],"approximately":[271],"8,000":[272],"predictions.":[273],"Additionally,":[274],"effectiveness":[278],"TOKI-guided":[280,327],"A2T,":[285],"state-of-the-art":[287],"classification.":[293],"Results":[294],"show":[295],"(1)":[297],"relying":[298],"cannot":[307],"effectively":[308],"distinguish":[309],"between":[310],"trustworthy":[311],"untrustworthy":[313],"predictions,":[314],"(2)":[315],"achieves":[317],"142%":[318],"higher":[319],"accuracy":[320],"than":[321,337],"baseline,":[324],"(3)":[326],"more":[332],"effective":[333],"fewer":[335],"perturbations":[336],"A2T.":[338]},"counts_by_year":[],"updated_date":"2026-03-27T05:58:40.876381","created_date":"2025-10-10T00:00:00"}