{"id":"https://openalex.org/W4415966292","doi":"https://doi.org/10.1145/3746252.3761289","title":"Contextual Attention Modulation: Towards Efficient Multi-Task Adaptation in Large Language Models","display_name":"Contextual Attention Modulation: Towards Efficient Multi-Task Adaptation in Large Language Models","publication_year":2025,"publication_date":"2025-11-07","ids":{"openalex":"https://openalex.org/W4415966292","doi":"https://doi.org/10.1145/3746252.3761289"},"language":null,"primary_location":{"id":"doi:10.1145/3746252.3761289","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3746252.3761289","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 34th ACM International Conference on Information and Knowledge Management","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2510.17705","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5107167297","display_name":"Dawei Pan","orcid":"https://orcid.org/0009-0008-7712-8658"},"institutions":[{"id":"https://openalex.org/I168719708","display_name":"City University of Hong Kong","ror":"https://ror.org/03q8dnn23","country_code":"HK","type":"education","lineage":["https://openalex.org/I168719708"]},{"id":"https://openalex.org/I82880672","display_name":"Beihang University","ror":"https://ror.org/00wk2mp56","country_code":"CN","type":"education","lineage":["https://openalex.org/I82880672"]}],"countries":["CN","HK"],"is_corresponding":false,"raw_author_name":"Dayan Pan","raw_affiliation_strings":["SCSE, Beihang University, Beijing, China, ERC of ACAT, MOE, Beijing, China, and City University of Hong Kong, Hong Kong, China"],"raw_orcid":"https://orcid.org/0009-0008-7712-8658","affiliations":[{"raw_affiliation_string":"SCSE, Beihang University, Beijing, China, ERC of ACAT, MOE, Beijing, China, and City University of Hong Kong, Hong Kong, China","institution_ids":["https://openalex.org/I168719708","https://openalex.org/I82880672"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Zhaoyang Fu","orcid":"https://orcid.org/0009-0004-7180-0977"},"institutions":[{"id":"https://openalex.org/I2250955327","display_name":"Huawei Technologies (China)","ror":"https://ror.org/00cmhce21","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250955327"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhaoyang Fu","raw_affiliation_strings":["Huawei Technologies Ltd., Shenzhen, China"],"raw_orcid":"https://orcid.org/0009-0004-7180-0977","affiliations":[{"raw_affiliation_string":"Huawei Technologies Ltd., Shenzhen, China","institution_ids":["https://openalex.org/I2250955327"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Jingyuan Wang","orcid":"https://orcid.org/0000-0003-0651-1592"},"institutions":[{"id":"https://openalex.org/I82880672","display_name":"Beihang University","ror":"https://ror.org/00wk2mp56","country_code":"CN","type":"education","lineage":["https://openalex.org/I82880672"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jingyuan Wang","raw_affiliation_strings":["SCSE, Beihang University, Beijing, China, Key Lab of DIM, MIIT, Beijing, China, and SEM, Beihang University, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0003-0651-1592","affiliations":[{"raw_affiliation_string":"SCSE, Beihang University, Beijing, China, Key Lab of DIM, MIIT, Beijing, China, and SEM, Beihang University, Beijing, China","institution_ids":["https://openalex.org/I82880672"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Xiao Han","orcid":"https://orcid.org/0000-0002-3478-964X"},"institutions":[{"id":"https://openalex.org/I55712492","display_name":"Zhejiang University of Technology","ror":"https://ror.org/02djqfd08","country_code":"CN","type":"education","lineage":["https://openalex.org/I55712492"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiao Han","raw_affiliation_strings":["Zhejiang University of Technology, Hangzhou, China"],"raw_orcid":"https://orcid.org/0000-0002-3478-964X","affiliations":[{"raw_affiliation_string":"Zhejiang University of Technology, Hangzhou, China","institution_ids":["https://openalex.org/I55712492"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Yue Zhu","orcid":"https://orcid.org/0009-0001-4776-5268"},"institutions":[{"id":"https://openalex.org/I2250955327","display_name":"Huawei Technologies (China)","ror":"https://ror.org/00cmhce21","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250955327"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yue Zhu","raw_affiliation_strings":["Huawei Technologies Ltd., Shenzhen, China"],"raw_orcid":"https://orcid.org/0009-0001-4776-5268","affiliations":[{"raw_affiliation_string":"Huawei Technologies Ltd., Shenzhen, China","institution_ids":["https://openalex.org/I2250955327"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100645854","display_name":"Xiangyu Zhao","orcid":"https://orcid.org/0000-0003-2926-4416"},"institutions":[{"id":"https://openalex.org/I168719708","display_name":"City University of Hong Kong","ror":"https://ror.org/03q8dnn23","country_code":"HK","type":"education","lineage":["https://openalex.org/I168719708"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Xiangyu Zhao","raw_affiliation_strings":["City University of Hong Kong, Hong Kong, China"],"raw_orcid":"https://orcid.org/0000-0003-2926-4416","affiliations":[{"raw_affiliation_string":"City University of Hong Kong, Hong Kong, China","institution_ids":["https://openalex.org/I168719708"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"2273","last_page":"2283"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.35569998621940613,"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":0.35569998621940613,"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":0.2786000072956085,"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/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.07180000096559525,"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/adaptation","display_name":"Adaptation (eye)","score":0.5855000019073486},{"id":"https://openalex.org/keywords/forgetting","display_name":"Forgetting","score":0.46650001406669617},{"id":"https://openalex.org/keywords/generalization","display_name":"Generalization","score":0.45350000262260437},{"id":"https://openalex.org/keywords/code","display_name":"Code (set theory)","score":0.453000009059906},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.42329999804496765},{"id":"https://openalex.org/keywords/resource","display_name":"Resource (disambiguation)","score":0.36820000410079956},{"id":"https://openalex.org/keywords/semantics","display_name":"Semantics (computer science)","score":0.36320000886917114}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7986000180244446},{"id":"https://openalex.org/C139807058","wikidata":"https://www.wikidata.org/wiki/Q352374","display_name":"Adaptation (eye)","level":2,"score":0.5855000019073486},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.48750001192092896},{"id":"https://openalex.org/C7149132","wikidata":"https://www.wikidata.org/wiki/Q1377840","display_name":"Forgetting","level":2,"score":0.46650001406669617},{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.45350000262260437},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.453000009059906},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.42329999804496765},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.40619999170303345},{"id":"https://openalex.org/C206345919","wikidata":"https://www.wikidata.org/wiki/Q20380951","display_name":"Resource (disambiguation)","level":2,"score":0.36820000410079956},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.36320000886917114},{"id":"https://openalex.org/C89611455","wikidata":"https://www.wikidata.org/wiki/Q6804646","display_name":"Mechanism (biology)","level":2,"score":0.350600004196167},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.3248000144958496},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.31139999628067017},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.3093999922275543},{"id":"https://openalex.org/C187303228","wikidata":"https://www.wikidata.org/wiki/Q867330","display_name":"Cyclomatic complexity","level":3,"score":0.29580000042915344},{"id":"https://openalex.org/C74172769","wikidata":"https://www.wikidata.org/wiki/Q1446839","display_name":"Routing (electronic design automation)","level":2,"score":0.2937000095844269},{"id":"https://openalex.org/C2777212361","wikidata":"https://www.wikidata.org/wiki/Q5127848","display_name":"Class (philosophy)","level":2,"score":0.28369998931884766},{"id":"https://openalex.org/C52970973","wikidata":"https://www.wikidata.org/wiki/Q2497134","display_name":"Adaptive system","level":2,"score":0.260699987411499},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.25279998779296875}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/3746252.3761289","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3746252.3761289","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 34th ACM International Conference on Information and Knowledge Management","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2510.17705","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2510.17705","pdf_url":"https://arxiv.org/pdf/2510.17705","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":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2510.17705","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2510.17705","pdf_url":"https://arxiv.org/pdf/2510.17705","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":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G1467331575","display_name":null,"funder_award_id":"72242101","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G2363765612","display_name":null,"funder_award_id":"72171013","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G3572663930","display_name":null,"funder_award_id":"72171013, 72222022, 72242101, 62502404","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G5662005453","display_name":null,"funder_award_id":"11218325","funder_id":"https://openalex.org/F4320335882","funder_display_name":"General Research Fund of Shanghai Normal University"},{"id":"https://openalex.org/G8299714314","display_name":null,"funder_award_id":"9229503","funder_id":"https://openalex.org/F4320309893","funder_display_name":"City University of Hong Kong"},{"id":"https://openalex.org/G8651611484","display_name":null,"funder_award_id":"72222022","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G8933230585","display_name":null,"funder_award_id":"JKF-2025017226182","funder_id":"https://openalex.org/F4320335787","funder_display_name":"Fundamental Research Funds for the Central Universities"}],"funders":[{"id":"https://openalex.org/F4320307285","display_name":"Impact Fund","ror":"https://ror.org/00jb20j87"},{"id":"https://openalex.org/F4320309893","display_name":"City University of Hong Kong","ror":"https://ror.org/03q8dnn23"},{"id":"https://openalex.org/F4320316083","display_name":"Tencent","ror":"https://ror.org/00hhjss72"},{"id":"https://openalex.org/F4320318398","display_name":"Ant Group","ror":null},{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320335787","display_name":"Fundamental Research Funds for the Central Universities","ror":null},{"id":"https://openalex.org/F4320335882","display_name":"General Research Fund of Shanghai Normal University","ror":null}],"has_content":{"grobid_xml":false,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4415966292.pdf"},"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Large":[0],"Language":[1],"Models":[2],"(LLMs)":[3],"possess":[4],"remarkable":[5],"generalization":[6],"capabilities":[7],"but":[8],"struggle":[9],"with":[10,18,101],"multi-task":[11,40,81],"adaptation,":[12,82],"particularly":[13],"in":[14,38,62],"balancing":[15],"knowledge":[16,115],"retention":[17],"task-specific":[19,66],"specialization.":[20],"Conventional":[21],"fine-tuning":[22],"methods":[23,35],"suffer":[24],"from":[25],"catastrophic":[26],"forgetting":[27],"and":[28,76,127,148],"substantial":[29],"resource":[30],"consumption,":[31],"while":[32,68],"existing":[33,136],"parameter-efficient":[34],"perform":[36],"suboptimally":[37],"complex":[39],"scenarios.":[41],"To":[42],"address":[43],"this,":[44],"we":[45],"propose":[46],"Contextual":[47,89],"Attention":[48,90],"Modulation":[49,91],"(CAM),":[50],"a":[51,96,109],"novel":[52],"mechanism":[53],"that":[54,131],"dynamically":[55],"modulates":[56],"the":[57],"representations":[58],"of":[59,143],"self-attention":[60],"modules":[61],"LLMs.":[63],"CAM":[64,83,99,105],"enhances":[65],"features":[67],"preserving":[69],"general":[70],"knowledge,":[71],"thereby":[72],"facilitating":[73],"more":[74],"effective":[75,80],"efficient":[77],"adaptation.":[78],"For":[79],"is":[84],"integrated":[85],"into":[86],"our":[87,132],"Hybrid":[88],"(HyCAM)":[92],"framework,":[93],"which":[94],"combines":[95],"shared,":[97],"full-parameter":[98],"module":[100],"multiple":[102],"specialized,":[103],"lightweight":[104],"modules,":[106],"enhanced":[107],"by":[108],"dynamic":[110],"routing":[111],"strategy":[112],"for":[113],"adaptive":[114],"fusion.":[116],"Extensive":[117],"experiments":[118],"on":[119],"heterogeneous":[120],"tasks,":[121],"including":[122],"question":[123],"answering,":[124],"code":[125,147],"generation,":[126],"logical":[128],"reasoning,":[129],"demonstrate":[130],"approach":[133],"significantly":[134],"outperforms":[135],"approaches,":[137],"achieving":[138],"an":[139],"average":[140],"performance":[141],"improvement":[142],"3.65%.":[144],"The":[145],"implemented":[146],"data":[149],"are":[150],"available":[151],"to":[152],"ease":[153],"reproducibility":[154],"at":[155],"https://github.com/Applied-Machine-Learning-Lab/HyCAM.":[156]},"counts_by_year":[],"updated_date":"2026-07-22T07:51:19.307946","created_date":"2025-10-22T00:00:00"}