{"id":"https://openalex.org/W7120051728","doi":"https://doi.org/10.48550/arxiv.2601.05038","title":"ArcAligner: Adaptive Recursive Aligner for Compressed Context Embeddings in RAG","display_name":"ArcAligner: Adaptive Recursive Aligner for Compressed Context Embeddings in RAG","publication_year":2026,"publication_date":"2026-01-08","ids":{"openalex":"https://openalex.org/W7120051728","doi":"https://doi.org/10.48550/arxiv.2601.05038"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2601.05038","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2601.05038","pdf_url":"https://arxiv.org/pdf/2601.05038","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":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"volume":null,"type":"preprint","indexed_in":["arxiv","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2601.05038","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5087080159","display_name":"Jianbo Li","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I204983213","display_name":"Harbin Institute of Technology","ror":"https://ror.org/01yqg2h08","country_code":"CN","type":"education","lineage":["https://openalex.org/I204983213"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Li, Jianbo","raw_affiliation_strings":["Harbin Institute of Technology , China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Harbin Institute of Technology , China","institution_ids":["https://openalex.org/I204983213"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5122707265","display_name":"Yi Da Jiang","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I204983213","display_name":"Harbin Institute of Technology","ror":"https://ror.org/01yqg2h08","country_code":"CN","type":"education","lineage":["https://openalex.org/I204983213"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jiang, Yi","raw_affiliation_strings":["Harbin Institute of Technology , China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Harbin Institute of Technology , China","institution_ids":["https://openalex.org/I204983213"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5122531690","display_name":"Sendong Zhao","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I204983213","display_name":"Harbin Institute of Technology","ror":"https://ror.org/01yqg2h08","country_code":"CN","type":"education","lineage":["https://openalex.org/I204983213"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhao, Sendong","raw_affiliation_strings":["Harbin Institute of Technology , China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Harbin Institute of Technology , China","institution_ids":["https://openalex.org/I204983213"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5122613943","display_name":"Bairui Hu","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I204983213","display_name":"Harbin Institute of Technology","ror":"https://ror.org/01yqg2h08","country_code":"CN","type":"education","lineage":["https://openalex.org/I204983213"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hu, Bairui","raw_affiliation_strings":["Harbin Institute of Technology , China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Harbin Institute of Technology , China","institution_ids":["https://openalex.org/I204983213"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5122526491","display_name":"Haochun Wang","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I204983213","display_name":"Harbin Institute of Technology","ror":"https://ror.org/01yqg2h08","country_code":"CN","type":"education","lineage":["https://openalex.org/I204983213"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wang, Haochun","raw_affiliation_strings":["Harbin Institute of Technology , China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Harbin Institute of Technology , China","institution_ids":["https://openalex.org/I204983213"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5140777709","display_name":"Bing Qin","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I204983213","display_name":"Harbin Institute of Technology","ror":"https://ror.org/01yqg2h08","country_code":"CN","type":"education","lineage":["https://openalex.org/I204983213"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Qin, Bing","raw_affiliation_strings":["Harbin Institute of Technology , China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Harbin Institute of Technology , China","institution_ids":["https://openalex.org/I204983213"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I204983213"],"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":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":0.989300012588501,"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":0.989300012588501,"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/T10286","display_name":"Information Retrieval and Search Behavior","score":0.00570000009611249,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"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":0.00279999990016222,"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/retrieval-augmented-generation","display_name":"retrieval-augmented generation","score":0.984000027179718},{"id":"https://openalex.org/keywords/context-compression","display_name":"context compression","score":0.9100000262260437},{"id":"https://openalex.org/keywords/adaptive-gating","display_name":"adaptive gating","score":0.7900000214576721},{"id":"https://openalex.org/keywords/recursive-alignment","display_name":"recursive alignment","score":0.8220000267028809},{"id":"https://openalex.org/keywords/long-document-retrieval","display_name":"long document retrieval","score":0.44600000977516174},{"id":"https://openalex.org/keywords/question-answering","display_name":"question answering","score":0.5879999995231628},{"id":"https://openalex.org/keywords/multi-hop-reasoning","display_name":"multi-hop reasoning","score":0.6930000185966492},{"id":"https://openalex.org/keywords/efficient-large-language-models","display_name":"efficient large language models","score":0.49300000071525574}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7914000153541565},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.6887000203132629},{"id":"https://openalex.org/C170858558","wikidata":"https://www.wikidata.org/wiki/Q1394144","display_name":"Automatic summarization","level":2,"score":0.6793000102043152},{"id":"https://openalex.org/C108010975","wikidata":"https://www.wikidata.org/wiki/Q500094","display_name":"Pruning","level":2,"score":0.5892000198364258},{"id":"https://openalex.org/C48145219","wikidata":"https://www.wikidata.org/wiki/Q1335365","display_name":"Security token","level":2,"score":0.5677000284194946},{"id":"https://openalex.org/C180016635","wikidata":"https://www.wikidata.org/wiki/Q2712821","display_name":"Compression (physics)","level":2,"score":0.5234000086784363},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.5069000124931335},{"id":"https://openalex.org/C78548338","wikidata":"https://www.wikidata.org/wiki/Q2493","display_name":"Data compression","level":2,"score":0.46540001034736633},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.40470001101493835},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.38769999146461487},{"id":"https://openalex.org/C163258240","wikidata":"https://www.wikidata.org/wiki/Q25342","display_name":"Power (physics)","level":2,"score":0.37790000438690186},{"id":"https://openalex.org/C183322885","wikidata":"https://www.wikidata.org/wiki/Q17007702","display_name":"Context model","level":3,"score":0.3727000057697296},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.365200012922287},{"id":"https://openalex.org/C43126263","wikidata":"https://www.wikidata.org/wiki/Q128751","display_name":"Source code","level":2,"score":0.3634999990463257},{"id":"https://openalex.org/C125411270","wikidata":"https://www.wikidata.org/wiki/Q18653","display_name":"Encoding (memory)","level":2,"score":0.35440000891685486},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.33880001306533813},{"id":"https://openalex.org/C2776207758","wikidata":"https://www.wikidata.org/wiki/Q5303302","display_name":"Downstream (manufacturing)","level":2,"score":0.3222000002861023},{"id":"https://openalex.org/C124304363","wikidata":"https://www.wikidata.org/wiki/Q673661","display_name":"Abstraction","level":2,"score":0.31949999928474426},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.2662999927997589},{"id":"https://openalex.org/C171268870","wikidata":"https://www.wikidata.org/wiki/Q1486676","display_name":"GRASP","level":2,"score":0.2653999924659729},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.2630000114440918},{"id":"https://openalex.org/C2780992000","wikidata":"https://www.wikidata.org/wiki/Q17016113","display_name":"Generator (circuit theory)","level":3,"score":0.2581999897956848}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2601.05038","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2601.05038","pdf_url":"https://arxiv.org/pdf/2601.05038","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":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2601.05038","doi":"https://doi.org/10.48550/arxiv.2601.05038","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2601.05038","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":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2601.05038","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2601.05038","pdf_url":"https://arxiv.org/pdf/2601.05038","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":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7120051728.pdf","grobid_xml":"https://content.openalex.org/works/W7120051728.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W4416033870","https://openalex.org/W7168016197","https://openalex.org/W4416034950","https://openalex.org/W4400668365","https://openalex.org/W4416610420","https://openalex.org/W4414691532","https://openalex.org/W7211909818","https://openalex.org/W4415795887","https://openalex.org/W4407953545","https://openalex.org/W4417280583"],"abstract_inverted_index":{"Retrieval-Augmented":[0],"Generation":[1],"(RAG)":[2],"helps":[3],"LLMs":[4],"stay":[5],"accurate,":[6],"but":[7],"feeding":[8],"long":[9],"documents":[10,40],"into":[11,41,80],"a":[12,49,76],"prompt":[13],"makes":[14],"the":[15,51,55,57,59,81,87,111,116],"model":[16,83,88],"slow":[17],"and":[18,29,135],"expensive.":[19],"This":[20],"has":[21],"motivated":[22],"context":[23,74,93],"compression,":[24],"ranging":[25],"from":[26],"token":[27],"pruning":[28],"summarization":[30],"to":[31,62,85],"embedding-based":[32],"compression.":[33],"While":[34],"researchers":[35],"have":[36],"tried":[37],"''compressing''":[38],"these":[39],"smaller":[42],"summaries":[43],"or":[44],"mathematical":[45],"embeddings,":[46],"there":[47],"is":[48,113,141],"catch:":[50],"more":[52,58],"you":[53],"compress":[54],"data,":[56],"LLM":[60],"struggles":[61],"understand":[63],"it.":[64],"To":[65],"address":[66],"this":[67],"challenge,":[68],"we":[69],"propose":[70],"ArcAligner":[71,123],"(Adaptive":[72],"recursive":[73],"*Aligner*),":[75],"lightweight":[77],"module":[78],"integrated":[79],"language":[82],"layers":[84],"help":[86],"better":[89],"utilize":[90],"highly":[91],"compressed":[92],"representations":[94],"for":[95],"downstream":[96],"generation.":[97],"It":[98],"uses":[99],"an":[100],"adaptive":[101],"''gating''":[102],"system":[103,117],"that":[104],"only":[105],"adds":[106],"extra":[107],"processing":[108],"power":[109],"when":[110],"information":[112],"complex,":[114],"keeping":[115],"fast.":[118],"Across":[119],"knowledge-intensive":[120],"QA":[121],"benchmarks,":[122],"consistently":[124],"beats":[125],"compression":[126,130],"baselines":[127],"at":[128],"comparable":[129],"rates,":[131],"especially":[132],"on":[133],"multi-hop":[134],"long-tail":[136],"settings.":[137],"The":[138],"source":[139],"code":[140],"publicly":[142],"available.":[143]},"counts_by_year":[],"updated_date":"2026-10-28T10:33:24.094632","created_date":"2026-01-10T00:00:00"}