{"id":"https://openalex.org/W4410636406","doi":"https://doi.org/10.1145/3701716.3717568","title":"Are Large Language Models Good Data Preprocessors?","display_name":"Are Large Language Models Good Data Preprocessors?","publication_year":2025,"publication_date":"2025-05-08","ids":{"openalex":"https://openalex.org/W4410636406","doi":"https://doi.org/10.1145/3701716.3717568"},"language":"en","primary_location":{"id":"doi:10.1145/3701716.3717568","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3701716.3717568","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3701716.3717568","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Companion Proceedings of the ACM on Web Conference 2025","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://dl.acm.org/doi/pdf/10.1145/3701716.3717568","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5007782698","display_name":"Elyas Meguellati","orcid":"https://orcid.org/0000-0003-1978-686X"},"institutions":[{"id":"https://openalex.org/I165143802","display_name":"The University of Queensland","ror":"https://ror.org/00rqy9422","country_code":"AU","type":"education","lineage":["https://openalex.org/I165143802"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Elyas Meguellati","raw_affiliation_strings":["The University of Queensland, Brisbane, Australia"],"raw_orcid":"https://orcid.org/0000-0003-1978-686X","affiliations":[{"raw_affiliation_string":"The University of Queensland, Brisbane, Australia","institution_ids":["https://openalex.org/I165143802"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5115002419","display_name":"Nardiena Pratama","orcid":"https://orcid.org/0009-0003-8710-4653"},"institutions":[{"id":"https://openalex.org/I165143802","display_name":"The University of Queensland","ror":"https://ror.org/00rqy9422","country_code":"AU","type":"education","lineage":["https://openalex.org/I165143802"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Nardiena Pratama","raw_affiliation_strings":["The University of Queensland, Brisbane, Australia"],"raw_orcid":"https://orcid.org/0009-0003-8710-4653","affiliations":[{"raw_affiliation_string":"The University of Queensland, Brisbane, Australia","institution_ids":["https://openalex.org/I165143802"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5070591850","display_name":"Shazia Sadiq","orcid":"https://orcid.org/0000-0001-6739-4145"},"institutions":[{"id":"https://openalex.org/I165143802","display_name":"The University of Queensland","ror":"https://ror.org/00rqy9422","country_code":"AU","type":"education","lineage":["https://openalex.org/I165143802"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Shazia Sadiq","raw_affiliation_strings":["The University of Queensland, Brisbane, Australia"],"raw_orcid":"https://orcid.org/0000-0001-6739-4145","affiliations":[{"raw_affiliation_string":"The University of Queensland, Brisbane, Australia","institution_ids":["https://openalex.org/I165143802"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5052565959","display_name":"Gianluca Demartini","orcid":"https://orcid.org/0000-0002-7311-3693"},"institutions":[{"id":"https://openalex.org/I165143802","display_name":"The University of Queensland","ror":"https://ror.org/00rqy9422","country_code":"AU","type":"education","lineage":["https://openalex.org/I165143802"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Gianluca Demartini","raw_affiliation_strings":["The University of Queensland, Brisbane, Australia"],"raw_orcid":"https://orcid.org/0000-0002-7311-3693","affiliations":[{"raw_affiliation_string":"The University of Queensland, Brisbane, Australia","institution_ids":["https://openalex.org/I165143802"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I165143802"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":3,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"2129","last_page":"2132"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.996999979019165,"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":0.996999979019165,"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/T13702","display_name":"Machine Learning in Healthcare","score":0.9933000206947327,"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/T11775","display_name":"COVID-19 diagnosis using AI","score":0.9779000282287598,"subfield":{"id":"https://openalex.org/subfields/2741","display_name":"Radiology, Nuclear Medicine and Imaging"},"field":{"id":"https://openalex.org/fields/27","display_name":"Medicine"},"domain":{"id":"https://openalex.org/domains/4","display_name":"Health Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8131350874900818},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.6305971741676331}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8131350874900818},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.6305971741676331}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3701716.3717568","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3701716.3717568","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3701716.3717568","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Companion Proceedings of the ACM on Web Conference 2025","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3701716.3717568","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3701716.3717568","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3701716.3717568","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Companion Proceedings of the ACM on Web Conference 2025","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G1561731934","display_name":null,"funder_award_id":"IC200100022","funder_id":"https://openalex.org/F4320323817","funder_display_name":"Universitas Brawijaya"}],"funders":[{"id":"https://openalex.org/F4320323817","display_name":"Universitas Brawijaya","ror":"https://ror.org/01wk3d929"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4410636406.pdf","grobid_xml":"https://content.openalex.org/works/W4410636406.grobid-xml"},"referenced_works_count":1,"referenced_works":["https://openalex.org/W4389267014"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W2390279801","https://openalex.org/W4391913857","https://openalex.org/W2358668433","https://openalex.org/W4396701345","https://openalex.org/W2376932109","https://openalex.org/W2001405890","https://openalex.org/W4396696052"],"abstract_inverted_index":{"High-quality":[0],"textual":[1,104],"training":[2],"data":[3,11,51,116,167,214,234],"is":[4,59],"essential":[5],"for":[6,50,203],"the":[7,84,103,112,163,178,185,188,191,196,201,207,227],"success":[8],"of":[9,67,86,106,114,151,187,193,211],"multimodal":[10],"processing":[12],"tasks,":[13],"yet":[14],"outputs":[15,105],"from":[16],"image":[17],"captioning":[18],"models":[19,49,129],"like":[20],"BLIP":[21,107],"and":[22,27,72,76,95,101,108,169,184,190,209],"GIT":[23],"often":[24],"contain":[25],"errors":[26],"anomalies":[28],"that":[29,149,159],"are":[30,154,181],"difficult":[31],"to":[32,62,99,165,183,226],"rectify":[33],"using":[34,47,143],"rule-based":[35],"methods.":[36],"While":[37,136],"recent":[38],"work":[39],"addressing":[40],"this":[41,80],"issue":[42],"has":[43],"predominantly":[44],"focused":[45],"on":[46,53,131,177],"GPT":[48],"preprocessing":[52,215,235],"relatively":[54],"simple":[55],"public":[56],"datasets,":[57,222],"there":[58],"a":[60,64],"need":[61,202],"explore":[63],"broader":[65],"range":[66],"Large":[68],"Language":[69],"Models":[70],"(LLMs)":[71],"tackle":[73],"more":[74],"challenging":[75,221],"diverse":[77],"datasets.":[78],"In":[79],"study,":[81],"we":[82],"investigate":[83],"use":[85],"multiple":[87],"LLMs,":[88],"including":[89],"LLaMA":[90],"3.1":[91],"70B,":[92],"GPT-4":[93],"Turbo,":[94],"Sonnet":[96],"3.5":[97],"v2":[98],"refine":[100],"clean":[102],"GIT.":[109],"We":[110],"assess":[111],"impact":[113],"LLM-assisted":[115],"cleaning":[117,168],"by":[118],"comparing":[119],"downstream-task":[120],"(SemEval":[121],"2024":[122],"Subtask":[123],"'Multilabel":[124],"Persuasion":[125],"Detection":[126],"in":[127,195,213],"Memes'')":[128],"trained":[130],"cleaned":[132],"versus":[133],"non-cleaned":[134],"data.":[135],"our":[137],"experimental":[138],"results":[139],"show":[140],"improvements":[141,153],"when":[142,218],"LLM-cleaned":[144],"captions,":[145],"statistical":[146],"tests":[147],"reveal":[148],"most":[150],"these":[152],"not":[155],"significant.":[156],"This":[157],"suggests":[158],"while":[160],"LLMs":[161,212,232],"have":[162],"potential":[164],"enhance":[166],"repairing,":[170],"their":[171],"effectiveness":[172],"may":[173],"be":[174],"limited":[175],"depending":[176],"context":[179],"they":[180],"applied":[182],"complexity":[186],"task":[189],"level":[192],"noise":[194],"text.":[197],"Our":[198],"findings":[199],"highlight":[200],"further":[204],"research":[205],"into":[206,233],"capabilities":[208],"limitations":[210],"pipelines,":[216],"especially":[217],"dealing":[219],"with":[220],"contributing":[223],"empirical":[224],"evidence":[225],"ongoing":[228],"discussion":[229],"about":[230],"integrating":[231],"pipelines.":[236]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":2}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}