{"id":"https://openalex.org/W4416018122","doi":"https://doi.org/10.1145/3746252.3760990","title":"A Cost-Aware Approach for Collaborating Large Language Models and Small Language Models","display_name":"A Cost-Aware Approach for Collaborating Large Language Models and Small Language Models","publication_year":2025,"publication_date":"2025-11-08","ids":{"openalex":"https://openalex.org/W4416018122","doi":"https://doi.org/10.1145/3746252.3760990"},"language":null,"primary_location":{"id":"doi:10.1145/3746252.3760990","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3746252.3760990","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":"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/A5101847862","display_name":"Zheng Li","orcid":"https://orcid.org/0000-0001-7840-8303"},"institutions":[{"id":"https://openalex.org/I881766915","display_name":"Nanjing University","ror":"https://ror.org/01rxvg760","country_code":"CN","type":"education","lineage":["https://openalex.org/I881766915"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Zheng Li","raw_affiliation_strings":["State Key Laboratory of Novel Software Technology, Nanjing University, Nanjing, Jiangsu, China"],"affiliations":[{"raw_affiliation_string":"State Key Laboratory of Novel Software Technology, Nanjing University, Nanjing, Jiangsu, China","institution_ids":["https://openalex.org/I881766915"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5076120553","display_name":"Xuyun Zhang","orcid":"https://orcid.org/0000-0001-7353-4159"},"institutions":[{"id":"https://openalex.org/I99043593","display_name":"Macquarie University","ror":"https://ror.org/01sf06y89","country_code":"AU","type":"education","lineage":["https://openalex.org/I99043593"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Xuyun Zhang","raw_affiliation_strings":["School of Computing, Macquarie University, Sydney, NSW, Australia"],"affiliations":[{"raw_affiliation_string":"School of Computing, Macquarie University, Sydney, NSW, Australia","institution_ids":["https://openalex.org/I99043593"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101279742","display_name":"Sheng Lu","orcid":"https://orcid.org/0009-0001-0750-9403"},"institutions":[{"id":"https://openalex.org/I881766915","display_name":"Nanjing University","ror":"https://ror.org/01rxvg760","country_code":"CN","type":"education","lineage":["https://openalex.org/I881766915"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Sheng Lu","raw_affiliation_strings":["State Key Laboratory of Novel Software Technology, Nanjing University, Nanjing, Jiangsu, China"],"affiliations":[{"raw_affiliation_string":"State Key Laboratory of Novel Software Technology, Nanjing University, Nanjing, Jiangsu, China","institution_ids":["https://openalex.org/I881766915"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5031478475","display_name":"Hua Deng","orcid":"https://orcid.org/0009-0006-4192-8894"},"institutions":[{"id":"https://openalex.org/I881766915","display_name":"Nanjing University","ror":"https://ror.org/01rxvg760","country_code":"CN","type":"education","lineage":["https://openalex.org/I881766915"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hua Deng","raw_affiliation_strings":["State Key Laboratory of Novel Software Technology, Nanjing University, Nanjing, Jiangsu, China"],"affiliations":[{"raw_affiliation_string":"State Key Laboratory of Novel Software Technology, Nanjing University, Nanjing, Jiangsu, China","institution_ids":["https://openalex.org/I881766915"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5043480330","display_name":"Hao Tian","orcid":"https://orcid.org/0000-0002-5335-5898"},"institutions":[{"id":"https://openalex.org/I881766915","display_name":"Nanjing University","ror":"https://ror.org/01rxvg760","country_code":"CN","type":"education","lineage":["https://openalex.org/I881766915"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hao Tian","raw_affiliation_strings":["State Key Laboratory of Novel Software Technology, Nanjing University, Nanjing, Jiangsu, China"],"affiliations":[{"raw_affiliation_string":"State Key Laboratory of Novel Software Technology, Nanjing University, Nanjing, Jiangsu, China","institution_ids":["https://openalex.org/I881766915"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5038791483","display_name":"Wanchun Dou","orcid":"https://orcid.org/0000-0003-4833-2023"},"institutions":[{"id":"https://openalex.org/I881766915","display_name":"Nanjing University","ror":"https://ror.org/01rxvg760","country_code":"CN","type":"education","lineage":["https://openalex.org/I881766915"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wanchun Dou","raw_affiliation_strings":["State Key Laboratory of Novel Software Technology, Nanjing University, Nanjing, Jiangsu, China"],"affiliations":[{"raw_affiliation_string":"State Key Laboratory of Novel Software Technology, Nanjing University, Nanjing, Jiangsu, China","institution_ids":["https://openalex.org/I881766915"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5101847862"],"corresponding_institution_ids":["https://openalex.org/I881766915"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.18364619,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1748","last_page":"1757"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.19939999282360077,"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":0.19939999282360077,"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":0.13989999890327454,"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/T11636","display_name":"Artificial Intelligence in Healthcare and Education","score":0.1039000004529953,"subfield":{"id":"https://openalex.org/subfields/2718","display_name":"Health Informatics"},"field":{"id":"https://openalex.org/fields/27","display_name":"Medicine"},"domain":{"id":"https://openalex.org/domains/4","display_name":"Health Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.7245000004768372},{"id":"https://openalex.org/keywords/sketch","display_name":"Sketch","score":0.5681999921798706},{"id":"https://openalex.org/keywords/rationality","display_name":"Rationality","score":0.4562999904155731},{"id":"https://openalex.org/keywords/path","display_name":"Path (computing)","score":0.44290000200271606},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.40849998593330383},{"id":"https://openalex.org/keywords/quality","display_name":"Quality (philosophy)","score":0.3952000141143799},{"id":"https://openalex.org/keywords/fuse","display_name":"Fuse (electrical)","score":0.37700000405311584},{"id":"https://openalex.org/keywords/service","display_name":"Service (business)","score":0.37040001153945923}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7684999704360962},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.7245000004768372},{"id":"https://openalex.org/C2779231336","wikidata":"https://www.wikidata.org/wiki/Q7534724","display_name":"Sketch","level":2,"score":0.5681999921798706},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.46320000290870667},{"id":"https://openalex.org/C201717286","wikidata":"https://www.wikidata.org/wiki/Q938185","display_name":"Rationality","level":2,"score":0.4562999904155731},{"id":"https://openalex.org/C2777735758","wikidata":"https://www.wikidata.org/wiki/Q817765","display_name":"Path (computing)","level":2,"score":0.44290000200271606},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.40849998593330383},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.3952000141143799},{"id":"https://openalex.org/C141353440","wikidata":"https://www.wikidata.org/wiki/Q182221","display_name":"Fuse (electrical)","level":2,"score":0.37700000405311584},{"id":"https://openalex.org/C2780378061","wikidata":"https://www.wikidata.org/wiki/Q25351891","display_name":"Service (business)","level":2,"score":0.37040001153945923},{"id":"https://openalex.org/C116537","wikidata":"https://www.wikidata.org/wiki/Q2169973","display_name":"Service provider","level":3,"score":0.3587999939918518},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.3125999867916107},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.3059000074863434},{"id":"https://openalex.org/C195344581","wikidata":"https://www.wikidata.org/wiki/Q2555318","display_name":"Automated reasoning","level":2,"score":0.2944999933242798},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.2939999997615814},{"id":"https://openalex.org/C89288958","wikidata":"https://www.wikidata.org/wiki/Q7301504","display_name":"Reasoning system","level":2,"score":0.2849999964237213},{"id":"https://openalex.org/C128838566","wikidata":"https://www.wikidata.org/wiki/Q275603","display_name":"Logic programming","level":2,"score":0.2809999883174896},{"id":"https://openalex.org/C175154964","wikidata":"https://www.wikidata.org/wiki/Q380077","display_name":"Task analysis","level":3,"score":0.2777000069618225},{"id":"https://openalex.org/C9616225","wikidata":"https://www.wikidata.org/wiki/Q3929429","display_name":"Semantic reasoner","level":2,"score":0.2775000035762787},{"id":"https://openalex.org/C20162079","wikidata":"https://www.wikidata.org/wiki/Q1151406","display_name":"Case-based reasoning","level":2,"score":0.26840001344680786},{"id":"https://openalex.org/C179603123","wikidata":"https://www.wikidata.org/wiki/Q1941921","display_name":"Modeling language","level":3,"score":0.2599000036716461},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.2583000063896179},{"id":"https://openalex.org/C2777508537","wikidata":"https://www.wikidata.org/wiki/Q7936620","display_name":"Visual reasoning","level":2,"score":0.25619998574256897}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3746252.3760990","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3746252.3760990","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"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":15,"referenced_works":["https://openalex.org/W2971196067","https://openalex.org/W3034850762","https://openalex.org/W4288055447","https://openalex.org/W4301393026","https://openalex.org/W4382246105","https://openalex.org/W4390873714","https://openalex.org/W4391136507","https://openalex.org/W4392560653","https://openalex.org/W4393147428","https://openalex.org/W4393152836","https://openalex.org/W4399534541","https://openalex.org/W4402670524","https://openalex.org/W4403582500","https://openalex.org/W4403791611","https://openalex.org/W4409362346"],"related_works":[],"abstract_inverted_index":{"The":[0],"emerging":[1],"reasoning":[2,46,53,181,194,217,241],"ability":[3],"of":[4,35,76,84,145,177,215,233,246],"large":[5],"language":[6],"models":[7],"(LLMs)":[8],"and":[9,67,126,151,197,243],"accompanying":[10],"commercial":[11],"applications":[12],"offer":[13],"a":[14,93,109,120,133],"promising":[15],"path":[16],"for":[17,48,123],"service":[18,58],"providers":[19,39],"to":[20,40,44,72,103,108,147,171,186,206,236],"deploy":[21],"intelligent":[22],"agents":[23],"on":[24,221],"their":[25],"own":[26],"products":[27],"through":[28],"API":[29,234],"calls.":[30],"However,":[31],"the":[32,51,74,81,88,101,115,142,161,164,174,188,193,198,213,216,231,240,244],"black-box":[33],"nature":[34],"LLMs":[36,66,125,237],"has":[37],"driven":[38],"try":[41],"prompt":[42,102,179],"tuning":[43],"improve":[45],"quality":[47],"competitiveness,":[49],"while":[50,238],"generated":[52,247],"logic":[54,195,202],"results":[55,91,220],"in":[56,92,190],"additional":[57],"costs.":[59],"Although":[60],"some":[61],"works":[62],"have":[63],"proposed":[64],"collaborating":[65,124],"Small":[68],"Language":[69],"Models":[70],"(SLMs)":[71],"reduce":[73,104],"frequency":[75],"LLM":[77,154,189],"calls,":[78],"most":[79],"overlook":[80],"actual":[82],"number":[83],"tokens":[85,105],"interacting":[86],"with":[87],"LLMs,":[89],"which":[90,140],"potentially":[94],"high":[95],"cost":[96,232],"still.":[97],"Furthermore,":[98],"directly":[99],"compressing":[100,167],"often":[106],"leads":[107],"significant":[110],"accuracy":[111,242],"loss.":[112],"To":[113],"address":[114],"above":[116],"challenges,":[117],"we":[118],"propose":[119],"cost-aware":[121],"approach":[122,228],"SLMs,":[127],"named":[128],"Coco.":[129],"In":[130],"our":[131,227],"method,":[132],"confidence-based":[134],"task":[135,149],"assignment":[136],"method":[137],"is":[138,156,204],"designed":[139],"leverages":[141],"result":[143],"confidence":[144],"SLMs":[146],"assess":[148],"complexity":[150],"determine":[152],"whether":[153],"involvement":[155],"necessary.":[157],"For":[158],"complex":[159],"tasks,":[160],"SLM":[162],"adapts":[163],"input":[165],"by":[166],"unnecessary":[168],"information":[169],"according":[170],"confidence.":[172],"Considering":[173],"potential":[175],"loss":[176],"accuracy,":[178],"tuning-based":[180],"optimization":[182],"methods":[183],"are":[184],"introduced":[185],"guide":[187],"generating":[191],"both":[192,210],"sketch":[196],"final":[199],"result.":[200],"Finally,":[201],"alignment":[203],"applied":[205],"fuse":[207],"sketches":[208],"from":[209],"models,":[211],"ensuring":[212,239],"rationality":[214],"logic.":[218,248],"Experimental":[219],"three":[222],"open-source":[223],"datasets":[224],"demonstrate":[225],"that":[226],"effectively":[229],"reduces":[230],"calls":[235],"reasonableness":[245]},"counts_by_year":[],"updated_date":"2026-03-07T16:01:11.037858","created_date":"2025-11-08T00:00:00"}
