{"id":"https://openalex.org/W4417516992","doi":"https://doi.org/10.48550/arxiv.2505.07460","title":"A Survey on Collaborative Mechanisms Between Large and Small Language Models","display_name":"A Survey on Collaborative Mechanisms Between Large and Small Language Models","publication_year":2025,"publication_date":"2025-05-12","ids":{"openalex":"https://openalex.org/W4417516992","doi":"https://doi.org/10.48550/arxiv.2505.07460"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2505.07460","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2505.07460","pdf_url":"https://arxiv.org/pdf/2505.07460","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"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"},"volume":null,"type":"preprint","is_traditional":true,"indexed_in":["arxiv","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2505.07460","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5120863046","display_name":"Yi Chen","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"government","lineage":["https://openalex.org/I19820366"]},{"id":"https://openalex.org/I4210165038","display_name":"University of Chinese Academy of Sciences","ror":"https://ror.org/05qbk4x57","country_code":"CN","type":"education","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210165038"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Chen, Yi","raw_affiliation_strings":["Chengdu Institute of Computer Applications , Chinese Academy of Sciences , Chengdu , China","University of Chinese Academy of Sciences , Beijing , China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Chengdu Institute of Computer Applications , Chinese Academy of Sciences , Chengdu , China","institution_ids":["https://openalex.org/I19820366"]},{"raw_affiliation_string":"University of Chinese Academy of Sciences , Beijing , China","institution_ids":["https://openalex.org/I4210165038"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5120863047","display_name":"JiaHao Zhao","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"government","lineage":["https://openalex.org/I19820366"]},{"id":"https://openalex.org/I4210165038","display_name":"University of Chinese Academy of Sciences","ror":"https://ror.org/05qbk4x57","country_code":"CN","type":"education","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210165038"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhao, JiaHao","raw_affiliation_strings":["Chengdu Institute of Computer Applications , Chinese Academy of Sciences , Chengdu , China","University of Chinese Academy of Sciences , Beijing , China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Chengdu Institute of Computer Applications , Chinese Academy of Sciences , Chengdu , China","institution_ids":["https://openalex.org/I19820366"]},{"raw_affiliation_string":"University of Chinese Academy of Sciences , Beijing , China","institution_ids":["https://openalex.org/I4210165038"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5120863048","display_name":"HaoHao Han","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"government","lineage":["https://openalex.org/I19820366"]},{"id":"https://openalex.org/I4210165038","display_name":"University of Chinese Academy of Sciences","ror":"https://ror.org/05qbk4x57","country_code":"CN","type":"education","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210165038"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Han, HaoHao","raw_affiliation_strings":["Chengdu Institute of Computer Applications , Chinese Academy of Sciences , Chengdu , China","University of Chinese Academy of Sciences , Beijing , China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Chengdu Institute of Computer Applications , Chinese Academy of Sciences , Chengdu , China","institution_ids":["https://openalex.org/I19820366"]},{"raw_affiliation_string":"University of Chinese Academy of Sciences , Beijing , China","institution_ids":["https://openalex.org/I4210165038"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":36,"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/T10036","display_name":"Advanced Neural Network Applications","score":0.5023999810218811,"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"}},"topics":[{"id":"https://openalex.org/T10036","display_name":"Advanced Neural Network Applications","score":0.5023999810218811,"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":0.24070000648498535,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.10159999877214432,"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/large-language-models","display_name":"large language models","score":0.9649999737739563},{"id":"https://openalex.org/keywords/small-language-models","display_name":"small language models","score":1.0},{"id":"https://openalex.org/keywords/edge-deployment","display_name":"edge deployment","score":0.6669999957084656},{"id":"https://openalex.org/keywords/resource-constrained-devices","display_name":"resource-constrained devices","score":0.7409999966621399},{"id":"https://openalex.org/keywords/model-distillation","display_name":"model distillation","score":0.6449999809265137},{"id":"https://openalex.org/keywords/model-fusion","display_name":"model fusion","score":0.7919999957084656},{"id":"https://openalex.org/keywords/pipeline-parallelism","display_name":"pipeline parallelism","score":0.6150000095367432},{"id":"https://openalex.org/keywords/routing","display_name":"routing","score":0.48500001430511475},{"id":"https://openalex.org/keywords/auxiliary-model","display_name":"auxiliary model","score":0.5529999732971191},{"id":"https://openalex.org/keywords/low-latency","display_name":"low latency","score":0.5899999737739563},{"id":"https://openalex.org/keywords/privacy","display_name":"privacy","score":0.7200000286102295},{"id":"https://openalex.org/keywords/personalization","display_name":"personalization","score":0.9300000071525574},{"id":"https://openalex.org/keywords/offline-operation","display_name":"offline operation","score":0.8410000205039978},{"id":"https://openalex.org/keywords/task-allocation","display_name":"task allocation","score":0.7519999742507935},{"id":"https://openalex.org/keywords/security-and-privacy","display_name":"privacy and security","score":0.7020000219345093}],"concepts":[{"id":"https://openalex.org/C105339364","wikidata":"https://www.wikidata.org/wiki/Q2297740","display_name":"Software deployment","level":2,"score":0.711899995803833},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7096999883651733},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.6141999959945679},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.5925999879837036},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.4562000036239624},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.4390000104904175},{"id":"https://openalex.org/C28719098","wikidata":"https://www.wikidata.org/wiki/Q44946","display_name":"Point (geometry)","level":2,"score":0.42800000309944153},{"id":"https://openalex.org/C206345919","wikidata":"https://www.wikidata.org/wiki/Q20380951","display_name":"Resource (disambiguation)","level":2,"score":0.42160001397132874},{"id":"https://openalex.org/C2779304628","wikidata":"https://www.wikidata.org/wiki/Q3503480","display_name":"Face (sociological concept)","level":2,"score":0.37610000371932983},{"id":"https://openalex.org/C100609095","wikidata":"https://www.wikidata.org/wiki/Q1335050","display_name":"Embodied cognition","level":2,"score":0.361299991607666},{"id":"https://openalex.org/C136197465","wikidata":"https://www.wikidata.org/wiki/Q1729295","display_name":"Variety (cybernetics)","level":2,"score":0.3172000050544739},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.31470000743865967},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.29919999837875366},{"id":"https://openalex.org/C139807058","wikidata":"https://www.wikidata.org/wiki/Q352374","display_name":"Adaptation (eye)","level":2,"score":0.29510000348091125},{"id":"https://openalex.org/C56739046","wikidata":"https://www.wikidata.org/wiki/Q192060","display_name":"Knowledge management","level":1,"score":0.28769999742507935},{"id":"https://openalex.org/C2983448237","wikidata":"https://www.wikidata.org/wiki/Q1078276","display_name":"Language understanding","level":2,"score":0.2818000018596649},{"id":"https://openalex.org/C29202148","wikidata":"https://www.wikidata.org/wiki/Q287260","display_name":"Resource allocation","level":2,"score":0.2770000100135803},{"id":"https://openalex.org/C3019252630","wikidata":"https://www.wikidata.org/wiki/Q6549547","display_name":"Limited resources","level":2,"score":0.26809999346733093},{"id":"https://openalex.org/C112930515","wikidata":"https://www.wikidata.org/wiki/Q4389547","display_name":"Risk analysis (engineering)","level":1,"score":0.2621999979019165},{"id":"https://openalex.org/C158154518","wikidata":"https://www.wikidata.org/wiki/Q7310970","display_name":"Relevance (law)","level":2,"score":0.26030001044273376},{"id":"https://openalex.org/C195094911","wikidata":"https://www.wikidata.org/wiki/Q14167904","display_name":"Process management","level":1,"score":0.25540000200271606},{"id":"https://openalex.org/C201995342","wikidata":"https://www.wikidata.org/wiki/Q682496","display_name":"Systems engineering","level":1,"score":0.2538999915122986}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2505.07460","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2505.07460","pdf_url":"https://arxiv.org/pdf/2505.07460","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"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"},{"id":"doi:10.48550/arxiv.2505.07460","doi":"https://doi.org/10.48550/arxiv.2505.07460","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2505.07460","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"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":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2505.07460","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2505.07460","pdf_url":"https://arxiv.org/pdf/2505.07460","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"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":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4417516992.pdf","grobid_xml":"https://content.openalex.org/works/W4417516992.grobid-xml"},"referenced_works_count":60,"referenced_works":["https://openalex.org/W2975059944","https://openalex.org/W4319166707","https://openalex.org/W4380993498","https://openalex.org/W4389650713","https://openalex.org/W4391156874","https://openalex.org/W4391272493","https://openalex.org/W4392019445","https://openalex.org/W4393968405","https://openalex.org/W4394948080","https://openalex.org/W4395443209","https://openalex.org/W4396813683","https://openalex.org/W4399151645","https://openalex.org/W4399837065","https://openalex.org/W4401203387","https://openalex.org/W4402672093","https://openalex.org/W4403747428","https://openalex.org/W4404341189","https://openalex.org/W4404571181","https://openalex.org/W4404649984","https://openalex.org/W4404783047","https://openalex.org/W4405094403","https://openalex.org/W4405767374","https://openalex.org/W4406093559","https://openalex.org/W4406316538","https://openalex.org/W4406317518","https://openalex.org/W4407123540","https://openalex.org/W4407185357","https://openalex.org/W4407308503","https://openalex.org/W4407310662","https://openalex.org/W4407569610","https://openalex.org/W4407820731","https://openalex.org/W4408564965","https://openalex.org/W4409601900","https://openalex.org/W4410636762","https://openalex.org/W4411120282","https://openalex.org/W4411403346","https://openalex.org/W4414579547","https://openalex.org/W4414629897","https://openalex.org/W4414648140","https://openalex.org/W4414836306","https://openalex.org/W4415109993","https://openalex.org/W4415150983","https://openalex.org/W4415161321","https://openalex.org/W4415201218","https://openalex.org/W4415307357","https://openalex.org/W4415798125","https://openalex.org/W4416042299","https://openalex.org/W4416043746","https://openalex.org/W4416052404","https://openalex.org/W4416118085","https://openalex.org/W4416728720","https://openalex.org/W4417226708","https://openalex.org/W4417279857","https://openalex.org/W6891877332","https://openalex.org/W6927434701","https://openalex.org/W7117958492","https://openalex.org/W7121445788","https://openalex.org/W7134817535","https://openalex.org/W7134960620","https://openalex.org/W7138113670"],"related_works":["https://openalex.org/W7092311463","https://openalex.org/W7125712265","https://openalex.org/W4417440855","https://openalex.org/W4407782026","https://openalex.org/W7160945993","https://openalex.org/W7124281694","https://openalex.org/W4406185100","https://openalex.org/W7165795016","https://openalex.org/W4407881031","https://openalex.org/W4403048355"],"abstract_inverted_index":{"Large":[0],"Language":[1,21],"Models":[2,22],"(LLMs)":[3],"deliver":[4],"powerful":[5],"AI":[6,51],"capabilities":[7],"but":[8],"face":[9],"deployment":[10],"challenges":[11,112],"due":[12],"to":[13,44],"high":[14],"resource":[15],"costs":[16],"and":[17,26,37,79,92,105,123,137,141,157],"latency,":[18,89],"whereas":[19],"Small":[20],"(SLMs)":[23],"offer":[24],"efficiency":[25],"deployability":[27],"at":[28],"the":[29,97,152],"cost":[30],"of":[31,64,155],"reduced":[32],"performance.":[33],"Collaboration":[34],"between":[35],"LLMs":[36],"SLMs":[38],"emerges":[39],"as":[40,147],"a":[41,61,148],"crucial":[42],"paradigm":[43],"synergistically":[45],"balance":[46],"these":[47],"trade-offs,":[48],"enabling":[49,77],"advanced":[50],"applications,":[52],"especially":[53],"on":[54],"resource-constrained":[55],"edge":[56],"devices.":[57],"This":[58],"survey":[59],"provides":[60],"comprehensive":[62],"overview":[63],"LLM-SLM":[65,145],"collaboration,":[66],"detailing":[67],"various":[68],"interaction":[69],"mechanisms":[70],"(pipeline,":[71],"routing,":[72],"auxiliary,":[73],"distillation,":[74],"fusion),":[75],"key":[76,149],"technologies,":[78],"diverse":[80],"application":[81],"scenarios":[82],"driven":[83],"by":[84],"on-device":[85],"needs":[86],"like":[87],"low":[88],"privacy,":[90],"personalization,":[91],"offline":[93],"operation.":[94],"While":[95],"highlighting":[96],"significant":[98],"potential":[99],"for":[100,151],"creating":[101],"more":[102,130],"efficient,":[103],"adaptable,":[104],"accessible":[106],"AI,":[107,143],"we":[108],"also":[109],"discuss":[110],"persistent":[111],"including":[113],"system":[114],"overhead,":[115],"inter-model":[116],"consistency,":[117],"robust":[118],"task":[119],"allocation,":[120],"evaluation":[121],"complexity,":[122],"security/privacy":[124],"concerns.":[125],"Future":[126],"directions":[127],"point":[128],"towards":[129],"intelligent":[131],"adaptive":[132],"frameworks,":[133],"deeper":[134],"model":[135],"fusion,":[136],"expansion":[138],"into":[139],"multimodal":[140],"embodied":[142],"positioning":[144],"collaboration":[146],"driver":[150],"next":[153],"generation":[154],"practical":[156],"ubiquitous":[158],"artificial":[159],"intelligence.":[160]},"counts_by_year":[{"year":2026,"cited_by_count":27},{"year":2025,"cited_by_count":9}],"updated_date":"2026-11-10T11:39:43.021295","created_date":"2025-10-10T00:00:00"}