{"id":"https://openalex.org/W7160606484","doi":"https://doi.org/10.48550/arxiv.2605.05285","title":"Attribution-Guided Continual Learning for Large Language Models","display_name":"Attribution-Guided Continual Learning for Large Language Models","publication_year":2026,"publication_date":"2026-05-06","ids":{"openalex":"https://openalex.org/W7160606484","doi":"https://doi.org/10.48550/arxiv.2605.05285"},"language":null,"primary_location":{"id":"doi:10.48550/arxiv.2605.05285","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2605.05285","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"article"},"type":"preprint","indexed_in":["datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://doi.org/10.48550/arxiv.2605.05285","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5103097958","display_name":"Yazheng Liu","orcid":"https://orcid.org/0009-0005-5573-6861"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Liu, Yazheng","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5135717656","display_name":"Yuxuan Wan","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wan, Yuxuan","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5135643731","display_name":"Rui Xu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xu, Rui","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5135652900","display_name":"Xi Zhang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhang, Xi","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5135693129","display_name":"Sihong Xie","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xie, Sihong","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5135672353","display_name":"Hui Xiong","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xiong, Hui","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":6,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.9193000197410583,"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/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.9193000197410583,"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":0.008999999612569809,"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"}},{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.007499999832361937,"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/forgetting","display_name":"Forgetting","score":0.7926999926567078},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.5353000164031982},{"id":"https://openalex.org/keywords/language-understanding","display_name":"Language understanding","score":0.46799999475479126},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.45899999141693115},{"id":"https://openalex.org/keywords/semantics","display_name":"Semantics (computer science)","score":0.34369999170303345},{"id":"https://openalex.org/keywords/training-set","display_name":"Training set","score":0.34150001406669617}],"concepts":[{"id":"https://openalex.org/C7149132","wikidata":"https://www.wikidata.org/wiki/Q1377840","display_name":"Forgetting","level":2,"score":0.7926999926567078},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.739799976348877},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5871000289916992},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.5353000164031982},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.47350001335144043},{"id":"https://openalex.org/C2983448237","wikidata":"https://www.wikidata.org/wiki/Q1078276","display_name":"Language understanding","level":2,"score":0.46799999475479126},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.45899999141693115},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.34369999170303345},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.34150001406669617},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3124000132083893},{"id":"https://openalex.org/C2780735816","wikidata":"https://www.wikidata.org/wiki/Q28324931","display_name":"Incremental learning","level":2,"score":0.3093000054359436},{"id":"https://openalex.org/C74672266","wikidata":"https://www.wikidata.org/wiki/Q815859","display_name":"Language acquisition","level":2,"score":0.28290000557899475},{"id":"https://openalex.org/C67186912","wikidata":"https://www.wikidata.org/wiki/Q367664","display_name":"Data modeling","level":2,"score":0.2581999897956848},{"id":"https://openalex.org/C77967617","wikidata":"https://www.wikidata.org/wiki/Q4677561","display_name":"Active learning (machine learning)","level":2,"score":0.2522999942302704},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.2517000138759613}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2605.05285","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2605.05285","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"article"}],"best_oa_location":{"id":"doi:10.48550/arxiv.2605.05285","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2605.05285","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Large":[0],"language":[1],"models":[2],"(LLMs)":[3],"often":[4],"suffer":[5],"from":[6],"catastrophic":[7,26],"forgetting":[8,27],"in":[9,45,76],"continual":[10,64,107],"learning:":[11],"after":[12],"learning":[13,102,108],"new":[14,103,128],"tasks":[15,91,122],"sequentially,":[16],"they":[17,50],"perform":[18],"worse":[19],"on":[20,106,127],"earlier":[21],"tasks.":[22,104,129],"Existing":[23],"methods":[24,37],"mitigate":[25],"by":[28],"data":[29],"replay,":[30],"parameter":[31,74],"freezing,":[32],"or":[33,58],"regularization.":[34],"However,":[35],"these":[36,82],"lack":[38],"semantic":[39],"awareness":[40],"of":[41,120],"internal":[42],"knowledge":[43],"distribution":[44],"LLMs.":[46,68],"As":[47],"a":[48],"result,":[49],"cannot":[51],"distinguish":[52],"parameters":[53],"that":[54,111],"should":[55],"be":[56],"preserved":[57],"updated.":[59],"We":[60],"propose":[61],"an":[62],"attribution-guided":[63],"fine-tuning":[65],"framework":[66],"for":[67,101],"Our":[69],"method":[70,113],"estimates":[71],"task-specific,":[72],"element-wise":[73],"importance":[75],"each":[77],"Transformer":[78],"layer":[79],"and":[80],"uses":[81],"scores":[83],"to":[84,89],"modulate":[85],"gradients.":[86],"Parameters":[87],"important":[88],"previous":[90],"receive":[92],"smaller":[93],"updates,":[94],"while":[95,123],"less":[96],"relevant":[97],"ones":[98],"remain":[99],"plastic":[100],"Experiments":[105],"benchmarks":[109],"show":[110],"our":[112],"consistently":[114],"outperforms":[115],"baselines,":[116],"achieving":[117],"better":[118],"retention":[119],"old":[121],"maintaining":[124],"competitive":[125],"performance":[126]},"counts_by_year":[],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2026-05-09T00:00:00"}