{"id":"https://openalex.org/W4406457873","doi":"https://doi.org/10.1109/bigdata62323.2024.10825537","title":"Zero-shot LLM-guided Counterfactual Generation: A Case Study on NLP Model Evaluation","display_name":"Zero-shot LLM-guided Counterfactual Generation: A Case Study on NLP Model Evaluation","publication_year":2024,"publication_date":"2024-12-15","ids":{"openalex":"https://openalex.org/W4406457873","doi":"https://doi.org/10.1109/bigdata62323.2024.10825537"},"language":"en","primary_location":{"id":"doi:10.1109/bigdata62323.2024.10825537","is_oa":false,"landing_page_url":"https://doi.org/10.1109/bigdata62323.2024.10825537","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE International Conference on Big Data (BigData)","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5103250573","display_name":"Amrita Bhattacharjee","orcid":"https://orcid.org/0000-0001-6117-6382"},"institutions":[{"id":"https://openalex.org/I55732556","display_name":"Arizona State University","ror":"https://ror.org/03efmqc40","country_code":"US","type":"education","lineage":["https://openalex.org/I55732556"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Amrita Bhattacharjee","raw_affiliation_strings":["Arizona State University,School of Computing and AI,Tempe,AZ,USA"],"affiliations":[{"raw_affiliation_string":"Arizona State University,School of Computing and AI,Tempe,AZ,USA","institution_ids":["https://openalex.org/I55732556"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5047078657","display_name":"Raha Moraffah","orcid":"https://orcid.org/0000-0002-6891-2925"},"institutions":[{"id":"https://openalex.org/I107077323","display_name":"Worcester Polytechnic Institute","ror":"https://ror.org/05ejpqr48","country_code":"US","type":"education","lineage":["https://openalex.org/I107077323"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Raha Moraffah","raw_affiliation_strings":["Worcester Polytechnic Institute,Department of Computer Science,Worcester,MA,USA"],"affiliations":[{"raw_affiliation_string":"Worcester Polytechnic Institute,Department of Computer Science,Worcester,MA,USA","institution_ids":["https://openalex.org/I107077323"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5035107313","display_name":"Joshua Garland","orcid":"https://orcid.org/0000-0002-6724-2755"},"institutions":[{"id":"https://openalex.org/I55732556","display_name":"Arizona State University","ror":"https://ror.org/03efmqc40","country_code":"US","type":"education","lineage":["https://openalex.org/I55732556"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Joshua Garland","raw_affiliation_strings":["Arizona State University,Global Security Initiative,Tempe,AZ,USA"],"affiliations":[{"raw_affiliation_string":"Arizona State University,Global Security Initiative,Tempe,AZ,USA","institution_ids":["https://openalex.org/I55732556"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100338946","display_name":"Huan Liu","orcid":"https://orcid.org/0000-0002-3264-7904"},"institutions":[{"id":"https://openalex.org/I55732556","display_name":"Arizona State University","ror":"https://ror.org/03efmqc40","country_code":"US","type":"education","lineage":["https://openalex.org/I55732556"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Huan Liu","raw_affiliation_strings":["Arizona State University,School of Computing and AI,Tempe,AZ,USA"],"affiliations":[{"raw_affiliation_string":"Arizona State University,School of Computing and AI,Tempe,AZ,USA","institution_ids":["https://openalex.org/I55732556"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5103250573"],"corresponding_institution_ids":["https://openalex.org/I55732556"],"apc_list":null,"apc_paid":null,"fwci":2.1822,"has_fulltext":false,"cited_by_count":6,"citation_normalized_percentile":{"value":0.89875299,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":98,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"1243","last_page":"1248"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11689","display_name":"Adversarial Robustness in Machine Learning","score":0.9948999881744385,"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":0.9948999881744385,"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/T11241","display_name":"Advanced Malware Detection Techniques","score":0.9929999709129333,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"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":0.9842000007629395,"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":[{"id":"https://openalex.org/keywords/shot","display_name":"Shot (pellet)","score":0.7051259279251099},{"id":"https://openalex.org/keywords/counterfactual-thinking","display_name":"Counterfactual thinking","score":0.6960155963897705},{"id":"https://openalex.org/keywords/zero","display_name":"Zero (linguistics)","score":0.6840795874595642},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6297690272331238},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6292383670806885},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.5565243363380432},{"id":"https://openalex.org/keywords/one-shot","display_name":"One shot","score":0.4868023097515106},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.40463587641716003},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.15228885412216187},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.08996438980102539},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.07601043581962585}],"concepts":[{"id":"https://openalex.org/C2778344882","wikidata":"https://www.wikidata.org/wiki/Q278938","display_name":"Shot (pellet)","level":2,"score":0.7051259279251099},{"id":"https://openalex.org/C108650721","wikidata":"https://www.wikidata.org/wiki/Q1783253","display_name":"Counterfactual thinking","level":2,"score":0.6960155963897705},{"id":"https://openalex.org/C2780813799","wikidata":"https://www.wikidata.org/wiki/Q3274237","display_name":"Zero (linguistics)","level":2,"score":0.6840795874595642},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6297690272331238},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6292383670806885},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5565243363380432},{"id":"https://openalex.org/C2992734406","wikidata":"https://www.wikidata.org/wiki/Q413267","display_name":"One shot","level":2,"score":0.4868023097515106},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.40463587641716003},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.15228885412216187},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.08996438980102539},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.07601043581962585},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C77805123","wikidata":"https://www.wikidata.org/wiki/Q161272","display_name":"Social psychology","level":1,"score":0.0},{"id":"https://openalex.org/C178790620","wikidata":"https://www.wikidata.org/wiki/Q11351","display_name":"Organic chemistry","level":1,"score":0.0},{"id":"https://openalex.org/C78519656","wikidata":"https://www.wikidata.org/wiki/Q101333","display_name":"Mechanical engineering","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/bigdata62323.2024.10825537","is_oa":false,"landing_page_url":"https://doi.org/10.1109/bigdata62323.2024.10825537","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE International Conference on Big Data (BigData)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":39,"referenced_works":["https://openalex.org/W1607035479","https://openalex.org/W1840435438","https://openalex.org/W2066770300","https://openalex.org/W2516809705","https://openalex.org/W2951936329","https://openalex.org/W2970453125","https://openalex.org/W2978017171","https://openalex.org/W3035507081","https://openalex.org/W3101155149","https://openalex.org/W3103873238","https://openalex.org/W3104423855","https://openalex.org/W3105928338","https://openalex.org/W3111711122","https://openalex.org/W3118781290","https://openalex.org/W3174057701","https://openalex.org/W4206060008","https://openalex.org/W4206379437","https://openalex.org/W4226278401","https://openalex.org/W4283318425","https://openalex.org/W4307079201","https://openalex.org/W4321392130","https://openalex.org/W4360836968","https://openalex.org/W4379468930","https://openalex.org/W4384662964","https://openalex.org/W4384918448","https://openalex.org/W4390041933","https://openalex.org/W4404782964","https://openalex.org/W6676984168","https://openalex.org/W6739585900","https://openalex.org/W6754655096","https://openalex.org/W6768299147","https://openalex.org/W6768851824","https://openalex.org/W6788175385","https://openalex.org/W6810738896","https://openalex.org/W6839025151","https://openalex.org/W6847076894","https://openalex.org/W6850936240","https://openalex.org/W6852584927","https://openalex.org/W6854866820"],"related_works":["https://openalex.org/W2497720472","https://openalex.org/W4292659306","https://openalex.org/W3044321615","https://openalex.org/W2806221744","https://openalex.org/W2326937258","https://openalex.org/W394267150","https://openalex.org/W2773965352","https://openalex.org/W4294892107","https://openalex.org/W2357748469","https://openalex.org/W2392917037"],"abstract_inverted_index":{"With":[0],"the":[1,76,107,155],"development":[2],"and":[3,30,53,67,103,109,143,165],"proliferation":[4],"of":[5,24,34,48,78,113,141,157],"large,":[6],"complex,":[7],"black-box":[8,167],"models":[9,29,82],"for":[10,64,84,120],"solving":[11],"many":[12],"natural":[13],"language":[14,81],"processing":[15],"(NLP)":[16],"tasks,":[17],"there":[18],"is":[19,50],"also":[20],"an":[21],"increasing":[22],"necessity":[23],"methods":[25],"to":[26,90,99],"stress-test":[27,91],"these":[28],"provide":[31],"some":[32],"degree":[33],"interpretability":[35],"or":[36,133],"explainability.":[37],"While":[38],"counterfactual":[39,86,161],"examples":[40],"are":[41],"useful":[42],"in":[43,61,71,88,125,151,163],"this":[44,72,101],"regard,":[45],"automated":[46],"generation":[47,87],"counterfactuals":[49,124],"a":[51,96,126,139],"data":[52,68],"resource":[54],"intensive":[55],"process,":[56],"that":[57,106],"may":[58],"be":[59,117],"infeasible":[60],"practice,":[62],"especially":[63],"new":[65],"tasks":[66,150],"domains.":[69],"Therefore,":[70],"work":[73],"we":[74,104,153],"explore":[75,154],"possibility":[77],"leveraging":[79],"large":[80],"(LLMs)":[83],"zero-shot":[85,127,160],"order":[89],"NLP":[92,168],"models.":[93],"We":[94],"propose":[95],"structured":[97],"pipeline":[98],"facilitate":[100],"generation,":[102],"hypothesize":[105],"instruction-following":[108],"textual":[110],"understanding":[111],"capabilities":[112],"recent":[114],"LLMs":[115,158],"can":[116],"effectively":[118],"leveraged":[119],"generating":[121],"high":[122],"quality":[123],"manner,":[128],"without":[129],"requiring":[130],"any":[131],"training":[132],"fine-tuning.":[134],"Through":[135],"comprehensive":[136],"experiments":[137],"on":[138],"variety":[140],"propreitary":[142],"open-source":[144],"LLMs,":[145],"along":[146],"with":[147],"various":[148],"downstream":[149],"NLP,":[152],"efficacy":[156],"as":[159],"generators":[162],"evaluating":[164],"explaining":[166],"models.<sup":[169],"xmlns:mml=\"http://www.w3.org/1998/Math/MathML\"":[170],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">1</sup>":[171]},"counts_by_year":[{"year":2025,"cited_by_count":6}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}