{"id":"https://openalex.org/W4415524602","doi":"https://doi.org/10.1109/mlsp62443.2025.11204312","title":"Tackling Distribution Shift in LLM via KILO: Knowledge-Instructed Learning for Continual Adaptation","display_name":"Tackling Distribution Shift in LLM via KILO: Knowledge-Instructed Learning for Continual Adaptation","publication_year":2025,"publication_date":"2025-08-31","ids":{"openalex":"https://openalex.org/W4415524602","doi":"https://doi.org/10.1109/mlsp62443.2025.11204312"},"language":null,"primary_location":{"id":"doi:10.1109/mlsp62443.2025.11204312","is_oa":false,"landing_page_url":"https://doi.org/10.1109/mlsp62443.2025.11204312","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE 35th International Workshop on Machine Learning for Signal Processing (MLSP)","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/A5120126797","display_name":"Ling Muttakhiroh","orcid":null},"institutions":[{"id":"https://openalex.org/I60158472","display_name":"Concordia University","ror":"https://ror.org/0420zvk78","country_code":"CA","type":"education","lineage":["https://openalex.org/I60158472"]}],"countries":["CA"],"is_corresponding":true,"raw_author_name":"Ling Muttakhiroh","raw_affiliation_strings":["Concordia University,Montreal,Canada"],"affiliations":[{"raw_affiliation_string":"Concordia University,Montreal,Canada","institution_ids":["https://openalex.org/I60158472"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5000617157","display_name":"Thomas Fevens","orcid":"https://orcid.org/0000-0003-1160-1429"},"institutions":[{"id":"https://openalex.org/I60158472","display_name":"Concordia University","ror":"https://ror.org/0420zvk78","country_code":"CA","type":"education","lineage":["https://openalex.org/I60158472"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Thomas Fevens","raw_affiliation_strings":["Concordia University,Montreal,Canada"],"affiliations":[{"raw_affiliation_string":"Concordia University,Montreal,Canada","institution_ids":["https://openalex.org/I60158472"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5120126797"],"corresponding_institution_ids":["https://openalex.org/I60158472"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.17008309,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"6"},"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":0.9257000088691711,"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":0.9257000088691711,"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/adaptability","display_name":"Adaptability","score":0.640500009059906},{"id":"https://openalex.org/keywords/adaptation","display_name":"Adaptation (eye)","score":0.6226999759674072},{"id":"https://openalex.org/keywords/domain","display_name":"Domain (mathematical analysis)","score":0.5216000080108643},{"id":"https://openalex.org/keywords/domain-knowledge","display_name":"Domain knowledge","score":0.43560001254081726},{"id":"https://openalex.org/keywords/domain-adaptation","display_name":"Domain adaptation","score":0.43459999561309814},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.38749998807907104},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.3610000014305115},{"id":"https://openalex.org/keywords/production","display_name":"Production (economics)","score":0.3569999933242798}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7638999819755554},{"id":"https://openalex.org/C177606310","wikidata":"https://www.wikidata.org/wiki/Q5674297","display_name":"Adaptability","level":2,"score":0.640500009059906},{"id":"https://openalex.org/C139807058","wikidata":"https://www.wikidata.org/wiki/Q352374","display_name":"Adaptation (eye)","level":2,"score":0.6226999759674072},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.603600025177002},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.5216000080108643},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4618000090122223},{"id":"https://openalex.org/C207685749","wikidata":"https://www.wikidata.org/wiki/Q2088941","display_name":"Domain knowledge","level":2,"score":0.43560001254081726},{"id":"https://openalex.org/C2776434776","wikidata":"https://www.wikidata.org/wiki/Q19246213","display_name":"Domain adaptation","level":3,"score":0.43459999561309814},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.38749998807907104},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.3610000014305115},{"id":"https://openalex.org/C2778348673","wikidata":"https://www.wikidata.org/wiki/Q739302","display_name":"Production (economics)","level":2,"score":0.3569999933242798},{"id":"https://openalex.org/C77967617","wikidata":"https://www.wikidata.org/wiki/Q4677561","display_name":"Active learning (machine learning)","level":2,"score":0.3375999927520752},{"id":"https://openalex.org/C175154964","wikidata":"https://www.wikidata.org/wiki/Q380077","display_name":"Task analysis","level":3,"score":0.2953999936580658},{"id":"https://openalex.org/C2777220311","wikidata":"https://www.wikidata.org/wiki/Q6423340","display_name":"Knowledge acquisition","level":2,"score":0.29429998993873596},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.2939999997615814},{"id":"https://openalex.org/C112972136","wikidata":"https://www.wikidata.org/wiki/Q7595718","display_name":"Stability (learning theory)","level":2,"score":0.28859999775886536},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.2865999937057495},{"id":"https://openalex.org/C2776544517","wikidata":"https://www.wikidata.org/wiki/Q189447","display_name":"Unexpected events","level":2,"score":0.2858999967575073},{"id":"https://openalex.org/C2780735816","wikidata":"https://www.wikidata.org/wiki/Q28324931","display_name":"Incremental learning","level":2,"score":0.28209999203681946},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.2777999937534332},{"id":"https://openalex.org/C12713177","wikidata":"https://www.wikidata.org/wiki/Q1900281","display_name":"Perspective (graphical)","level":2,"score":0.27219998836517334},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.2687999904155731},{"id":"https://openalex.org/C2777211547","wikidata":"https://www.wikidata.org/wiki/Q17141490","display_name":"Training (meteorology)","level":2,"score":0.2637999951839447},{"id":"https://openalex.org/C40506919","wikidata":"https://www.wikidata.org/wiki/Q7452469","display_name":"Sequence learning","level":2,"score":0.2590999901294708}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/mlsp62443.2025.11204312","is_oa":false,"landing_page_url":"https://doi.org/10.1109/mlsp62443.2025.11204312","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE 35th International Workshop on Machine Learning for Signal Processing (MLSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":17,"referenced_works":["https://openalex.org/W2963123047","https://openalex.org/W2997200074","https://openalex.org/W3021931813","https://openalex.org/W3034503922","https://openalex.org/W3099215402","https://openalex.org/W3127228978","https://openalex.org/W3196731672","https://openalex.org/W3200852434","https://openalex.org/W4287890137","https://openalex.org/W4361001766","https://openalex.org/W4385567084","https://openalex.org/W4385573116","https://openalex.org/W4389523957","https://openalex.org/W4400190992","https://openalex.org/W4401208776","https://openalex.org/W4402827393","https://openalex.org/W4410371768"],"related_works":[],"abstract_inverted_index":{"Large":[0],"Language":[1],"Models":[2],"(LLMs)":[3],"often":[4],"suffer":[5],"from":[6],"performance":[7],"degradation":[8],"when":[9],"faced":[10],"with":[11,40],"domain":[12,130],"shifts,":[13],"primarily":[14],"due":[15],"to":[16,56,128],"catastrophic":[17],"forgetting.":[18],"In":[19],"this":[20],"work,":[21],"we":[22],"propose":[23],"KILO":[24,52,89],"(Knowledge-Instructed":[25],"Learning":[26],"for":[27],"Continual":[28],"Adaptation),":[29],"a":[30],"novel":[31],"continual":[32,95,134],"learning":[33,135],"framework":[34],"that":[35,88],"integrates":[36],"dynamic":[37],"knowledge":[38,47,123],"graphs":[39],"instruction":[41,126],"tuning.":[42],"By":[43],"leveraging":[44],"retrieved":[45],"domain-specific":[46],"as":[48],"guidance":[49],"during":[50],"training,":[51],"enhances":[53],"both":[54],"adaptability":[55],"new":[57],"domains":[58],"and":[59,71,83,99,112,125],"retention":[60,110],"of":[61,103,120],"previously":[62],"acquired":[63],"knowledge.":[64],"We":[65],"pretrain":[66],"our":[67],"model":[68],"on":[69],"WikiText-103":[70],"evaluate":[72],"sequential":[73],"adaptation":[74],"across":[75],"four":[76],"diverse":[77],"target":[78],"domains:":[79],"BioASQ,":[80],"SciQ,":[81],"TweetEval,":[82],"MIND.":[84],"Our":[85],"experiments":[86],"demonstrate":[87],"consistently":[90],"outperforms":[91],"strong":[92],"baselines,":[93],"including":[94],"fine-tuning,":[96],"ERNIE":[97],"2.0,":[98],"CPT,":[100],"in":[101,133],"terms":[102],"backward":[104],"transfer,":[105,107],"forward":[106],"F1":[108],"score,":[109],"rate,":[111],"training":[113],"efficiency.":[114],"These":[115],"results":[116],"highlight":[117],"the":[118],"effectiveness":[119],"combining":[121],"structured":[122],"retrieval":[124],"prompting":[127],"overcome":[129],"shift":[131],"challenges":[132],"scenarios.":[136]},"counts_by_year":[],"updated_date":"2026-03-07T16:01:11.037858","created_date":"2025-10-24T00:00:00"}