{"id":"https://openalex.org/W4409657110","doi":"https://doi.org/10.1145/3696410.3714687","title":"Mitigating Forgetting in Adapting Pre-trained Language Models to Text Processing Tasks via Consistency Alignment","display_name":"Mitigating Forgetting in Adapting Pre-trained Language Models to Text Processing Tasks via Consistency Alignment","publication_year":2025,"publication_date":"2025-04-22","ids":{"openalex":"https://openalex.org/W4409657110","doi":"https://doi.org/10.1145/3696410.3714687"},"language":"en","primary_location":{"id":"doi:10.1145/3696410.3714687","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3696410.3714687","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3696410.3714687","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the ACM on Web Conference 2025","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/10.1145/3696410.3714687","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5012712688","display_name":"Jianqi Gao","orcid":"https://orcid.org/0000-0002-9840-7866"},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jianqi Gao","raw_affiliation_strings":["Shanghai Jiao Tong University, Shanghai, China"],"raw_orcid":"https://orcid.org/0000-0002-9840-7866","affiliations":[{"raw_affiliation_string":"Shanghai Jiao Tong University, Shanghai, China","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Hao Wu","orcid":"https://orcid.org/0009-0004-3145-044X"},"institutions":[{"id":"https://openalex.org/I113940042","display_name":"Shanghai University","ror":"https://ror.org/006teas31","country_code":"CN","type":"education","lineage":["https://openalex.org/I113940042"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hao Wu","raw_affiliation_strings":["Shanghai University, Shanghai, China"],"raw_orcid":"https://orcid.org/0009-0004-3145-044X","affiliations":[{"raw_affiliation_string":"Shanghai University, Shanghai, China","institution_ids":["https://openalex.org/I113940042"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5038516431","display_name":"Yiu\u2010ming Cheung","orcid":"https://orcid.org/0000-0001-7629-4648"},"institutions":[{"id":"https://openalex.org/I141568987","display_name":"Hong Kong Baptist University","ror":"https://ror.org/0145fw131","country_code":"HK","type":"education","lineage":["https://openalex.org/I141568987"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Yiu-ming Cheung","raw_affiliation_strings":["Hong Kong Baptist University, Hong Kong, Hong Kong"],"raw_orcid":"https://orcid.org/0000-0001-7629-4648","affiliations":[{"raw_affiliation_string":"Hong Kong Baptist University, Hong Kong, Hong Kong","institution_ids":["https://openalex.org/I141568987"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100648774","display_name":"Jian Cao","orcid":"https://orcid.org/0000-0002-0036-9436"},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jian Cao","raw_affiliation_strings":["Shanghai Jiao Tong University, Shanghai, China"],"raw_orcid":"https://orcid.org/0000-0002-0036-9436","affiliations":[{"raw_affiliation_string":"Shanghai Jiao Tong University, Shanghai, China","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5062917240","display_name":"Hang Yu","orcid":"https://orcid.org/0000-0003-3444-9992"},"institutions":[{"id":"https://openalex.org/I113940042","display_name":"Shanghai University","ror":"https://ror.org/006teas31","country_code":"CN","type":"education","lineage":["https://openalex.org/I113940042"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hang Yu","raw_affiliation_strings":["Shanghai University, Shanghai, China"],"raw_orcid":"https://orcid.org/0000-0003-3444-9992","affiliations":[{"raw_affiliation_string":"Shanghai University, Shanghai, China","institution_ids":["https://openalex.org/I113940042"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5022901289","display_name":"Yonggang Zhang","orcid":"https://orcid.org/0000-0002-4080-7592"},"institutions":[{"id":"https://openalex.org/I141568987","display_name":"Hong Kong Baptist University","ror":"https://ror.org/0145fw131","country_code":"HK","type":"education","lineage":["https://openalex.org/I141568987"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Yonggang Zhang","raw_affiliation_strings":["Hong Kong Baptist University, Hong Kong, Hong Kong"],"raw_orcid":"https://orcid.org/0000-0002-4080-7592","affiliations":[{"raw_affiliation_string":"Hong Kong Baptist University, Hong Kong, Hong Kong","institution_ids":["https://openalex.org/I141568987"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":4.3671,"has_fulltext":true,"cited_by_count":3,"citation_normalized_percentile":{"value":0.93791205,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":95,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"3492","last_page":"3504"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.9997000098228455,"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":0.9997000098228455,"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/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.9993000030517578,"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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9969000220298767,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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":0.8320415019989014},{"id":"https://openalex.org/keywords/forgetting","display_name":"Forgetting","score":0.7159907817840576},{"id":"https://openalex.org/keywords/consistency","display_name":"Consistency (knowledge bases)","score":0.6526088118553162},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.5971062183380127},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.47485804557800293},{"id":"https://openalex.org/keywords/cognitive-psychology","display_name":"Cognitive psychology","score":0.1027241051197052},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.08077198266983032}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8320415019989014},{"id":"https://openalex.org/C7149132","wikidata":"https://www.wikidata.org/wiki/Q1377840","display_name":"Forgetting","level":2,"score":0.7159907817840576},{"id":"https://openalex.org/C2776436953","wikidata":"https://www.wikidata.org/wiki/Q5163215","display_name":"Consistency (knowledge bases)","level":2,"score":0.6526088118553162},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5971062183380127},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.47485804557800293},{"id":"https://openalex.org/C180747234","wikidata":"https://www.wikidata.org/wiki/Q23373","display_name":"Cognitive psychology","level":1,"score":0.1027241051197052},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.08077198266983032}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/3696410.3714687","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3696410.3714687","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3696410.3714687","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the ACM on Web Conference 2025","raw_type":"proceedings-article"},{"id":"pmh:oai:repository.hkust.edu.hk:1783.1-170853","is_oa":false,"landing_page_url":"http://repository.hkust.edu.hk/ir/Record/1783.1-170853","pdf_url":null,"source":{"id":"https://openalex.org/S4306401796","display_name":"Rare & Special e-Zone (The Hong Kong University of Science and Technology)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I200769079","host_organization_name":"Hong Kong University of Science and Technology","host_organization_lineage":["https://openalex.org/I200769079"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Conference paper"}],"best_oa_location":{"id":"doi:10.1145/3696410.3714687","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3696410.3714687","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3696410.3714687","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the ACM on Web Conference 2025","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G5847459458","display_name":null,"funder_award_id":"YG2024QNB05","funder_id":"https://openalex.org/F4320322999","funder_display_name":"Shanghai Jiao Tong University"}],"funders":[{"id":"https://openalex.org/F4320322999","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4409657110.pdf","grobid_xml":"https://content.openalex.org/works/W4409657110.grobid-xml"},"referenced_works_count":47,"referenced_works":["https://openalex.org/W1593271688","https://openalex.org/W2116522068","https://openalex.org/W2160204597","https://openalex.org/W2473930607","https://openalex.org/W2560647685","https://openalex.org/W2591922431","https://openalex.org/W2600463316","https://openalex.org/W2798991696","https://openalex.org/W2888482885","https://openalex.org/W2951902588","https://openalex.org/W2963748441","https://openalex.org/W2966087730","https://openalex.org/W2980708516","https://openalex.org/W2981842822","https://openalex.org/W2981852735","https://openalex.org/W3003627389","https://openalex.org/W3007041883","https://openalex.org/W3008051686","https://openalex.org/W3035524453","https://openalex.org/W3041561163","https://openalex.org/W3042857057","https://openalex.org/W3044438666","https://openalex.org/W3092288641","https://openalex.org/W3100156920","https://openalex.org/W3109116076","https://openalex.org/W3116231956","https://openalex.org/W3155368131","https://openalex.org/W3156476125","https://openalex.org/W3176512019","https://openalex.org/W3187071356","https://openalex.org/W3205809313","https://openalex.org/W3212062446","https://openalex.org/W3212560468","https://openalex.org/W4200182268","https://openalex.org/W4212926655","https://openalex.org/W4226418765","https://openalex.org/W4226426325","https://openalex.org/W4229453513","https://openalex.org/W4285546152","https://openalex.org/W4288089799","https://openalex.org/W4386290290","https://openalex.org/W4388430352","https://openalex.org/W4390873543","https://openalex.org/W4396794067","https://openalex.org/W4404742943","https://openalex.org/W6600195515","https://openalex.org/W6796502740"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W4289718052","https://openalex.org/W2164121020","https://openalex.org/W2145559838","https://openalex.org/W2905319430","https://openalex.org/W3116498279","https://openalex.org/W4287549553","https://openalex.org/W3204019825"],"abstract_inverted_index":{"There":[0],"are":[1],"a":[2,80],"large":[3],"number":[4],"of":[5,61,91,103,207,222],"text":[6],"processing":[7],"tasks":[8,32,46,228],"in":[9,42,94,106,154],"web":[10],"applications,":[11],"such":[12],"as":[13,85],"sentiment":[14],"classification,":[15],"summary":[16],"extraction,":[17],"and":[18,45,50,71,113,118,127,170,190,210,229,235],"question":[19],"answering.":[20],"Recently,":[21],"fine-tuning":[22,51,54],"pre-trained":[23],"language":[24],"models":[25],"(PLMs)":[26],"to":[27,29,39,109,122,139,178,184,202],"adapt":[28],"downstream":[30],"text-processing":[31],"has":[33],"attracted":[34],"much":[35],"attention.":[36],"However,":[37,174],"due":[38],"the":[40,48,53,68,101,110,115,119,124,133,141,147,155,166,175,180,185,188,195,204,208,211,220],"differences":[41],"data,":[43],"model,":[44],"between":[47,168,187],"pre-training":[49,62,104,125,142,148,189],"processes,":[52],"process":[55,149],"may":[56,65],"suffer":[57],"from":[58],"catastrophic":[59],"forgetting":[60],"knowledge,":[63],"which":[64,158],"implicitly":[66],"limit":[67],"model's":[69],"performance":[70],"generalization":[72],"ability.":[73],"To":[74,193],"address":[75],"these":[76],"challenges,":[77],"we":[78,197],"propose":[79],"novel":[81,163],"dual-model":[82],"framework,":[83],"termed":[84],"consistency":[86],"alignment":[87],"(CoAi).":[88],"The":[89],"insight":[90,164],"CoAi":[92,145,223],"lies":[93],"building":[95],"an":[96,199],"auxiliary":[97,120,134,181,200,212],"model":[98,117,121,135,171,182],"that":[99],"simulates":[100,146],"distribution":[102,206],"knowledge":[105,126,129],"real-time":[107],"according":[108],"current":[111],"task,":[112],"co-training":[114],"task-specific":[116,128,191,209],"balance":[123],"during":[130],"fine-tuning.":[131],"Specifically,":[132],"is":[136,159],"constructed":[137],"on-the-fly":[138],"maintain":[140],"knowledge.":[143,192],"Subsequently,":[144],"by":[150,215],"performing":[151],"distributional":[152],"exploration":[153],"parameter":[156,172],"space,":[157],"built":[160],"upon":[161],"our":[162],"into":[165],"transformation":[167],"data":[169],"space.":[173],"objectives":[176],"leveraged":[177],"construct":[179],"lead":[183],"misalignment":[186],"alleviate":[194],"inconsistency,":[196],"employ":[198],"variable":[201],"align":[203],"prediction":[205],"models,":[213],"inspired":[214],"constrastive":[216],"clustering.":[217],"We":[218],"validate":[219],"effectiveness":[221],"on":[224],"nine":[225],"classic":[226],"classification":[227],"three":[230],"generation":[231],"tasks,":[232],"showing":[233],"consistent":[234],"significant":[236],"improvements":[237],"compared":[238],"with":[239],"state-of-the-art":[240],"methods.":[241]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":2}],"updated_date":"2026-07-02T09:51:11.867554","created_date":"2025-10-10T00:00:00"}