{"id":"https://openalex.org/W7128740602","doi":"https://doi.org/10.48448/8cne-ep05","title":"LiteLong: Resource-Efficient Long-Context Data Synthesis for LLMs","display_name":"LiteLong: Resource-Efficient Long-Context Data Synthesis for LLMs","publication_year":2026,"publication_date":"2026-01-07","ids":{"openalex":"https://openalex.org/W7128740602","doi":"https://doi.org/10.48448/8cne-ep05"},"language":"en","primary_location":{"id":"doi:10.48448/8cne-ep05","doi":"https://doi.org/10.48448/8cne-ep05","is_oa":true,"landing_page_url":"https://doi.org/10.48448/8cne-ep05","pdf_url":null,"source":{"id":"https://openalex.org/S7407053148","display_name":"Underline Science Inc.","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Audiovisual"},"volume":null,"type":"other","indexed_in":["datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://doi.org/10.48448/8cne-ep05","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5125741655","display_name":"Association for Artificial Intelligence 2026","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Association for Artificial Intelligence 2026","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5125766775","display_name":"Guo Binghui","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Binghui, Guo","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5126220102","display_name":"Ziyang 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/I4210156404","display_name":"Institute of Information Engineering","ror":"https://ror.org/04r53se39","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210156404"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Chen, Ziyang","raw_affiliation_strings":["Institute of Information Engineering, Chinese Academy of Sciences"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute of Information Engineering, Chinese Academy of Sciences","institution_ids":["https://openalex.org/I19820366","https://openalex.org/I4210156404"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5125728492","display_name":"Chaochen Gao","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"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Gao, Chaochen","raw_affiliation_strings":["Chinese Academy of Sciences"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Chinese Academy of Sciences","institution_ids":["https://openalex.org/I19820366"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5120391811","display_name":"Junlong Jia","orcid":"https://orcid.org/0000-0002-5725-3397","observed_orcids":["https://orcid.org/0000-0002-5725-3397"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jia, Junlong","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5121665871","display_name":"Donghui Jin","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jin, Donghui","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5089315011","display_name":"Zhong-zhi Li","orcid":null,"observed_orcids":[]},"institutions":[{"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":"Li, Zhong-Zhi","raw_affiliation_strings":["University of Chinese Academy of Sciences"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Chinese Academy of Sciences","institution_ids":["https://openalex.org/I4210165038"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5125710763","display_name":"Zijia Lin","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Lin, Zijia","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5130771471","display_name":"Weinong Wang","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wang, Weinong","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5125766873","display_name":"Xing Wu","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wu, Xing","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5125768215","display_name":"haotian Xu","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I4401726856","display_name":"Xiaohongshu (Little Red Book) (China)","ror":"https://ror.org/02apw2076","country_code":"CN","type":"company","lineage":["https://openalex.org/I4401726856"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xu, haotian","raw_affiliation_strings":["xiaohongshu"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"xiaohongshu","institution_ids":["https://openalex.org/I4401726856"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5125693572","display_name":"Debing Zhang","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhang, Debing","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"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/T10028","display_name":"Topic Modeling","score":0.9926999807357788,"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":0.9926999807357788,"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":0.00419999985024333,"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":0.0010999999940395355,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/large-language-models","display_name":"large language models","score":0.7509999871253967},{"id":"https://openalex.org/keywords/multi-agent-debate","display_name":"multi-agent debate","score":0.7429999709129333},{"id":"https://openalex.org/keywords/bm25-retrieval","display_name":"BM25 retrieval","score":0.984000027179718}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7584999799728394},{"id":"https://openalex.org/C77618280","wikidata":"https://www.wikidata.org/wiki/Q1155772","display_name":"Scheme (mathematics)","level":2,"score":0.4571000039577484},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4496000111103058},{"id":"https://openalex.org/C2779304628","wikidata":"https://www.wikidata.org/wiki/Q3503480","display_name":"Face (sociological concept)","level":2,"score":0.4230000078678131},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.4196999967098236},{"id":"https://openalex.org/C67186912","wikidata":"https://www.wikidata.org/wiki/Q367664","display_name":"Data modeling","level":2,"score":0.4147000014781952},{"id":"https://openalex.org/C89611455","wikidata":"https://www.wikidata.org/wiki/Q6804646","display_name":"Mechanism (biology)","level":2,"score":0.38089999556541443},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.34049999713897705},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3361999988555908},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.3327000141143799},{"id":"https://openalex.org/C66024118","wikidata":"https://www.wikidata.org/wiki/Q1122506","display_name":"Computational model","level":2,"score":0.3192000091075897},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.31209999322891235},{"id":"https://openalex.org/C2778348673","wikidata":"https://www.wikidata.org/wiki/Q739302","display_name":"Production (economics)","level":2,"score":0.28029999136924744},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.2784999907016754},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.27480000257492065},{"id":"https://openalex.org/C144986985","wikidata":"https://www.wikidata.org/wiki/Q871236","display_name":"Hierarchical database model","level":2,"score":0.2660999894142151},{"id":"https://openalex.org/C2778137410","wikidata":"https://www.wikidata.org/wiki/Q2732820","display_name":"Government (linguistics)","level":2,"score":0.2513999938964844},{"id":"https://openalex.org/C56739046","wikidata":"https://www.wikidata.org/wiki/Q192060","display_name":"Knowledge management","level":1,"score":0.25060001015663147},{"id":"https://openalex.org/C100463513","wikidata":"https://www.wikidata.org/wiki/Q5227322","display_name":"Data model (GIS)","level":2,"score":0.25060001015663147}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48448/8cne-ep05","doi":"https://doi.org/10.48448/8cne-ep05","is_oa":true,"landing_page_url":"https://doi.org/10.48448/8cne-ep05","pdf_url":null,"source":{"id":"https://openalex.org/S7407053148","display_name":"Underline Science Inc.","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Audiovisual"}],"best_oa_location":{"id":"doi:10.48448/8cne-ep05","doi":"https://doi.org/10.48448/8cne-ep05","is_oa":true,"landing_page_url":"https://doi.org/10.48448/8cne-ep05","pdf_url":null,"source":{"id":"https://openalex.org/S7407053148","display_name":"Underline Science Inc.","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Audiovisual"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W7082272248","https://openalex.org/W4406779184","https://openalex.org/W4399252456","https://openalex.org/W4414844056","https://openalex.org/W7079662155","https://openalex.org/W6979283010","https://openalex.org/W6910880916","https://openalex.org/W4417090038","https://openalex.org/W4399358068","https://openalex.org/W7082278606"],"abstract_inverted_index":{"High-quality":[0],"long-context":[1,36,107,121,138],"data":[2,37,122,131],"is":[3],"essential":[4],"for":[5,34],"training":[6,94],"large":[7],"language":[8,139],"models":[9],"(LLMs)":[10],"capable":[11],"of":[12,25],"processing":[13],"extensive":[14],"documents,":[15],"yet":[16],"existing":[17],"synthesis":[18,123],"approaches":[19],"using":[20],"relevance-based":[21],"aggregation":[22],"face":[23],"challenges":[24],"computational":[26,129],"efficiency.":[27],"We":[28],"present":[29],"LiteLong,":[30],"a":[31,55,63],"resource-efficient":[32],"method":[33],"synthesizing":[35],"through":[38],"structured":[39],"topic":[40,58],"organization":[41],"and":[42,60,89,99,109,130],"multi-agent":[43],"debate.":[44],"Our":[45],"approach":[46],"leverages":[47],"the":[48],"BISAC":[49],"book":[50],"classification":[51],"system":[52],"to":[53,69,85],"provide":[54],"comprehensive":[56],"hierarchical":[57],"organization,":[59],"then":[61],"employs":[62],"debate":[64],"mechanism":[65],"with":[66,113],"multiple":[67],"LLMs":[68],"generate":[70],"diverse,":[71],"high-quality":[72,120],"topics":[73],"within":[74],"this":[75],"structure.":[76],"For":[77],"each":[78],"topic,":[79],"we":[80],"use":[81],"lightweight":[82],"BM25":[83],"retrieval":[84],"obtain":[86],"relevant":[87],"documents":[88],"concatenate":[90],"them":[91],"into":[92],"128K-token":[93],"samples.":[95],"Experiments":[96],"on":[97],"HELMET":[98],"Ruler":[100],"benchmarks":[101],"demonstrate":[102],"that":[103],"LiteLong":[104,118],"achieves":[105],"competitive":[106],"performance":[108],"can":[110],"seamlessly":[111],"integrate":[112],"other":[114],"long-dependency":[115],"enhancement":[116],"methods.":[117],"makes":[119],"more":[124],"accessible":[125],"by":[126],"reducing":[127],"both":[128],"engineering":[132],"costs,":[133],"facilitating":[134],"further":[135],"research":[136],"in":[137],"training.":[140]},"counts_by_year":[],"updated_date":"2026-10-28T10:33:24.094632","created_date":"2026-02-13T00:00:00"}