{"id":"https://openalex.org/W4412877224","doi":"https://doi.org/10.1145/3711896.3736871","title":"Calibrating Pre-trained Language Classifiers on LLM-generated Noisy Labels via Iterative Refinement","display_name":"Calibrating Pre-trained Language Classifiers on LLM-generated Noisy Labels via Iterative Refinement","publication_year":2025,"publication_date":"2025-08-03","ids":{"openalex":"https://openalex.org/W4412877224","doi":"https://doi.org/10.1145/3711896.3736871"},"language":"en","primary_location":{"id":"doi:10.1145/3711896.3736871","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3711896.3736871","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3711896.3736871","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 31st ACM SIGKDD Conference on Knowledge Discovery and Data Mining V.2","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://dl.acm.org/doi/pdf/10.1145/3711896.3736871","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5015193833","display_name":"Liqin Ye","orcid":null},"institutions":[{"id":"https://openalex.org/I130701444","display_name":"Georgia Institute of Technology","ror":"https://ror.org/01zkghx44","country_code":"US","type":"education","lineage":["https://openalex.org/I130701444"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Liqin Ye","raw_affiliation_strings":["School of Computational Science & Engineering, Georgia Institute of Technology, Atlanta, Georgia, USA"],"affiliations":[{"raw_affiliation_string":"School of Computational Science & Engineering, Georgia Institute of Technology, Atlanta, Georgia, USA","institution_ids":["https://openalex.org/I130701444"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5017623662","display_name":"Agam Shah","orcid":"https://orcid.org/0000-0002-9062-2430"},"institutions":[{"id":"https://openalex.org/I130701444","display_name":"Georgia Institute of Technology","ror":"https://ror.org/01zkghx44","country_code":"US","type":"education","lineage":["https://openalex.org/I130701444"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Agam Shah","raw_affiliation_strings":["School of Computational Science & Engineering, Georgia Institute of Technology, Atlanta, Georgia, USA"],"affiliations":[{"raw_affiliation_string":"School of Computational Science & Engineering, Georgia Institute of Technology, Atlanta, Georgia, USA","institution_ids":["https://openalex.org/I130701444"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100460272","display_name":"Chao Zhang","orcid":"https://orcid.org/0000-0003-3009-598X"},"institutions":[{"id":"https://openalex.org/I130701444","display_name":"Georgia Institute of Technology","ror":"https://ror.org/01zkghx44","country_code":"US","type":"education","lineage":["https://openalex.org/I130701444"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Chao Zhang","raw_affiliation_strings":["School of Computational Science & Engineering, Georgia Institute of Technology, Atlanta, Georgia, USA"],"affiliations":[{"raw_affiliation_string":"School of Computational Science & Engineering, Georgia Institute of Technology, Atlanta, Georgia, USA","institution_ids":["https://openalex.org/I130701444"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5029248881","display_name":"Sudheer Chava","orcid":"https://orcid.org/0000-0001-8330-682X"},"institutions":[{"id":"https://openalex.org/I130701444","display_name":"Georgia Institute of Technology","ror":"https://ror.org/01zkghx44","country_code":"US","type":"education","lineage":["https://openalex.org/I130701444"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Sudheer Chava","raw_affiliation_strings":["Scheller College of Business, Georgia Institute of Technology, Atlanta, Georgia, USA"],"affiliations":[{"raw_affiliation_string":"Scheller College of Business, Georgia Institute of Technology, Atlanta, Georgia, USA","institution_ids":["https://openalex.org/I130701444"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5015193833"],"corresponding_institution_ids":["https://openalex.org/I130701444"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.09325393,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"3598","last_page":"3609"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12535","display_name":"Machine Learning and Data Classification","score":0.9994999766349792,"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/T12535","display_name":"Machine Learning and Data Classification","score":0.9994999766349792,"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/T12072","display_name":"Machine Learning and Algorithms","score":0.9833999872207642,"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/T11550","display_name":"Text and Document Classification Technologies","score":0.9760000109672546,"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/computer-science","display_name":"Computer science","score":0.7639838457107544},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6197214722633362},{"id":"https://openalex.org/keywords/iterative-refinement","display_name":"Iterative refinement","score":0.5036076903343201},{"id":"https://openalex.org/keywords/iterative-method","display_name":"Iterative method","score":0.4405061602592468},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.43136078119277954},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3700464069843292},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.35482507944107056},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3476329445838928},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.25628501176834106}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7639838457107544},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6197214722633362},{"id":"https://openalex.org/C2779982483","wikidata":"https://www.wikidata.org/wiki/Q6094420","display_name":"Iterative refinement","level":2,"score":0.5036076903343201},{"id":"https://openalex.org/C159694833","wikidata":"https://www.wikidata.org/wiki/Q2321565","display_name":"Iterative method","level":2,"score":0.4405061602592468},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.43136078119277954},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3700464069843292},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.35482507944107056},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3476329445838928},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.25628501176834106}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3711896.3736871","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3711896.3736871","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3711896.3736871","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 31st ACM SIGKDD Conference on Knowledge Discovery and Data Mining V.2","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3711896.3736871","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3711896.3736871","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3711896.3736871","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 31st ACM SIGKDD Conference on Knowledge Discovery and Data Mining V.2","raw_type":"proceedings-article"},"sustainable_development_goals":[{"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4","score":0.7200000286102295}],"awards":[{"id":"https://openalex.org/G1726583756","display_name":"III: Small: Go Beyond Short-term Dependency and Homogeneity: A General-Purpose Transformer Recipe for Multi-Domain Heterogeneous Sequential Data Analysis","funder_award_id":"2008334","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G4460996906","display_name":"III: Medium: Towards Data-Efficient Decision-Focused Learning: A Modularized Pre-Training and Fine-Tuning Approach","funder_award_id":"2403240","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G4987246806","display_name":"CAREER: Accelerating Spatial Network Design: An Uncertainty-Driven Predict-and-Optimize Learning Framework","funder_award_id":"2144338","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G6484623147","display_name":"III: Medium: Collaborative Research: Principled Uncertainty Quantification in Deep Learning Models for Time Series Analysis","funder_award_id":"2106961","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G6671297155","display_name":null,"funder_award_id":"CAREER","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G848032724","display_name":null,"funder_award_id":"Science","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"}],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"},{"id":"https://openalex.org/F4320309321","display_name":"Georgia Institute of Technology","ror":"https://ror.org/01zkghx44"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4412877224.pdf","grobid_xml":"https://content.openalex.org/works/W4412877224.grobid-xml"},"referenced_works_count":23,"referenced_works":["https://openalex.org/W12634471","https://openalex.org/W1493526108","https://openalex.org/W1921293667","https://openalex.org/W2070246124","https://openalex.org/W2769041395","https://openalex.org/W2959716049","https://openalex.org/W2964292098","https://openalex.org/W3034185248","https://openalex.org/W3171635822","https://openalex.org/W3172399575","https://openalex.org/W4285290744","https://openalex.org/W4312305885","https://openalex.org/W4378420555","https://openalex.org/W4380686953","https://openalex.org/W4384662964","https://openalex.org/W4385565569","https://openalex.org/W4385571929","https://openalex.org/W4389524416","https://openalex.org/W4391841474","https://openalex.org/W4404781989","https://openalex.org/W4404783774","https://openalex.org/W4406458485","https://openalex.org/W6602601291"],"related_works":["https://openalex.org/W2788561539","https://openalex.org/W1771726367","https://openalex.org/W2034475059","https://openalex.org/W144062141","https://openalex.org/W3006775069","https://openalex.org/W2895720711","https://openalex.org/W2159155511","https://openalex.org/W82507644","https://openalex.org/W2528330837","https://openalex.org/W1562083549"],"abstract_inverted_index":{"The":[0],"traditional":[1],"process":[2],"of":[3,47,154,171,179,191],"creating":[4],"labeled":[5,26],"datasets":[6,27,167],"is":[7,66,73,195],"labor-intensive":[8],"and":[9,93,139,162,173],"expensive.Recent":[10],"breakthroughs":[11],"in":[12,24,83,135],"open-source":[13],"large":[14],"language":[15,32],"models":[16],"(LLMs)":[17],"have":[18],"opened":[19],"up":[20],"a":[21,52,145,189],"new":[22],"avenue":[23],"generating":[25],"automatically":[28],"for":[29,185],"various":[30],"natural":[31],"processing":[33],"(NLP)":[34],"tasks,":[35],"providing":[36],"an":[37,41,169],"alternative":[38],"to":[39,56,68,75,77,113],"such":[40,48],"expensive":[42],"annotation":[43],"process.However,":[44],"the":[45,63,115,152,155,177],"reliability":[46],"auto-generated":[49],"labels":[50,87],"remains":[51],"significant":[53],"concern":[54],"due":[55],"inherent":[57],"inaccuracies.When":[58],"learning":[59,84],"from":[60,85],"noisy":[61,86,124,142,165],"labels,":[62],"model's":[64],"generalization":[65],"likely":[67],"be":[69],"harmed":[70],"as":[71],"it":[72],"prone":[74],"overfit":[76],"those":[78],"label":[79,97,129,133,166],"noises.While":[80],"previous":[81],"studies":[82],"mainly":[88],"focus":[89],"on":[90,159,197],"synthetic":[91],"noise":[92,98],"real-world":[94],"noise,":[95],"LLM-generated":[96,123,164],"receives":[99],"less":[100],"attention.In":[101],"this":[102],"paper,":[103],"we":[104],"propose":[105],"SiDyP:":[106],"Simplex":[107],"Label":[108],"Diffusion":[109],"with":[110],"Dynamic":[111],"Prior":[112],"calibrate":[114],"classifier's":[116],"prediction,":[117],"thus":[118],"enhancing":[119],"its":[120],"robustness":[121],"towards":[122],"labels.SiDyP":[125],"retrieves":[126],"potential":[127],"true":[128],"candidates":[130,143],"by":[131,168,181],"neighborhood":[132],"distribution":[134],"text":[136],"embedding":[137],"space":[138],"iteratively":[140],"refines":[141],"using":[144],"simplex":[146],"diffusion":[147],"model.Our":[148],"framework":[149],"can":[150],"increase":[151],"performance":[153],"BERT":[156],"classifier":[157],"fine-tuned":[158],"both":[160],"zero-shot":[161],"few-shot":[163],"average":[170],"7.21%":[172],"7.30%":[174],"respectively.We":[175],"demonstrate":[176],"effectiveness":[178],"SiDyP":[180],"conducting":[182],"extensive":[183],"benchmarking":[184],"different":[186],"LLMs":[187],"over":[188],"variety":[190],"NLP":[192],"tasks.Our":[193],"code":[194],"available":[196],"GitHub":[198],"1":[199],".":[200]},"counts_by_year":[],"updated_date":"2026-04-10T15:06:20.359241","created_date":"2025-10-10T00:00:00"}