{"id":"https://openalex.org/W7225186367","doi":"https://doi.org/10.13053/cys-30-3-6608","title":"A Lightweight Extractive Compression Pipeline for Long-Context Retrieval-Augmented Generation","display_name":"A Lightweight Extractive Compression Pipeline for Long-Context Retrieval-Augmented Generation","publication_year":2026,"publication_date":"2026-09-29","ids":{"openalex":"https://openalex.org/W7225186367","doi":"https://doi.org/10.13053/cys-30-3-6608"},"language":"es","primary_location":{"id":"doi:10.13053/cys-30-3-6608","doi":"https://doi.org/10.13053/cys-30-3-6608","is_oa":false,"landing_page_url":"https://doi.org/10.13053/cys-30-3-6608","pdf_url":null,"source":{"id":"https://openalex.org/S61446325","display_name":"Computaci\u00f3n y Sistemas","issn_l":"1405-5546","issn":["1405-5546","2007-9737"],"is_oa":false,"is_in_doaj":false,"is_core":true,"listed_in":["cwts-core","dongbi-c","latindex","norway-1","poland-40","russia-white-list-4","scielo"],"host_organization":"https://openalex.org/P4310319599","host_organization_name":"National Polytechnic Institute","host_organization_lineage":["https://openalex.org/P4310319599"],"host_organization_lineage_names":["National Polytechnic Institute"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Computaci\u00f3n y Sistemas","raw_type":"journal-article"},"volume":null,"type":"article","is_traditional":true,"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/A5160529969","display_name":"Alikhan Zhamankhan","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Alikhan Zhamankhan","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5073124571","display_name":"Iskander Akhmetov","orcid":"https://orcid.org/0000-0002-3221-9352","observed_orcids":["https://orcid.org/0000-0002-3221-9352"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Iskander Akhmetov","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5160433234","display_name":"Alex Pak","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Alex Pak","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5118271121","display_name":"Assel Zhaxylykova","orcid":"https://orcid.org/0009-0009-8487-1164","observed_orcids":["https://orcid.org/0009-0009-8487-1164"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Assel Zhaxylykova","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5049701126","display_name":"Alexander F. Gelbukh","orcid":"https://orcid.org/0000-0001-7845-9039","observed_orcids":["https://orcid.org/0000-0001-7845-9039"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Alexander Gelbukh","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.0,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"30","issue":"3","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":0.9711999893188477,"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":0.9711999893188477,"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":0.019700000062584877,"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/T13083","display_name":"Advanced Text Analysis Techniques","score":0.0034000000450760126,"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/retrieval-augmented-generation","display_name":"retrieval-augmented generation","score":0.9179999828338623},{"id":"https://openalex.org/keywords/extractive-summarization","display_name":"extractive summarization","score":0.9430000185966492},{"id":"https://openalex.org/keywords/multi-hop-question-answering","display_name":"multi-hop question answering","score":0.9679999947547913},{"id":"https://openalex.org/keywords/computational-efficiency","display_name":"computational efficiency","score":0.5080000162124634}],"concepts":[{"id":"https://openalex.org/C43521106","wikidata":"https://www.wikidata.org/wiki/Q2165493","display_name":"Pipeline (software)","level":2,"score":0.5404999852180481},{"id":"https://openalex.org/C180016635","wikidata":"https://www.wikidata.org/wiki/Q2712821","display_name":"Compression (physics)","level":2,"score":0.4993000030517578},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.44119998812675476},{"id":"https://openalex.org/C199639397","wikidata":"https://www.wikidata.org/wiki/Q1788588","display_name":"Engineering drawing","level":1,"score":0.3107999861240387},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.3091999888420105},{"id":"https://openalex.org/C78548338","wikidata":"https://www.wikidata.org/wiki/Q2493","display_name":"Data compression","level":2,"score":0.27480000257492065},{"id":"https://openalex.org/C204366326","wikidata":"https://www.wikidata.org/wiki/Q3027650","display_name":"Deformation (meteorology)","level":2,"score":0.259799987077713},{"id":"https://openalex.org/C175309249","wikidata":"https://www.wikidata.org/wiki/Q725864","display_name":"Pipeline transport","level":2,"score":0.25870001316070557},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.2563000023365021},{"id":"https://openalex.org/C18762648","wikidata":"https://www.wikidata.org/wiki/Q42213","display_name":"Work (physics)","level":2,"score":0.2547000050544739},{"id":"https://openalex.org/C127313418","wikidata":"https://www.wikidata.org/wiki/Q1069","display_name":"Geology","level":0,"score":0.25060001015663147}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.13053/cys-30-3-6608","doi":"https://doi.org/10.13053/cys-30-3-6608","is_oa":false,"landing_page_url":"https://doi.org/10.13053/cys-30-3-6608","pdf_url":null,"source":{"id":"https://openalex.org/S61446325","display_name":"Computaci\u00f3n y Sistemas","issn_l":"1405-5546","issn":["1405-5546","2007-9737"],"is_oa":false,"is_in_doaj":false,"is_core":true,"listed_in":["cwts-core","dongbi-c","latindex","norway-1","poland-40","russia-white-list-4","scielo"],"host_organization":"https://openalex.org/P4310319599","host_organization_name":"National Polytechnic Institute","host_organization_lineage":["https://openalex.org/P4310319599"],"host_organization_lineage_names":["National Polytechnic Institute"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Computaci\u00f3n y Sistemas","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W4416060764","https://openalex.org/W7224577501","https://openalex.org/W4412945615","https://openalex.org/W4412888692","https://openalex.org/W7223491947","https://openalex.org/W4402671518","https://openalex.org/W4402671835","https://openalex.org/W4416034950","https://openalex.org/W4412886724","https://openalex.org/W7120051728"],"abstract_inverted_index":{"Long":[0],"contexts":[1],"in":[2,122],"Retrieval-Augmented":[3],"Generation":[4],"(RAG)":[5],"cause":[6],"high":[7],"latency":[8],"and":[9,26,45,62],"computational":[10,106],"costs.":[11],"We":[12],"propose":[13],"a":[14,30,52,96],"lightweight,":[15],"extractive":[16],"sentence-level":[17],"summarization":[18],"method":[19,94,110],"that":[20],"extracts":[21],"the":[22,87,93,109,119,127],"top-k":[23],"relevant":[24],"sentences":[25,36],"expands":[27],"them":[28],"with":[29,51,78],"dynamic":[31],"window":[32,54],"(w)":[33],"of":[34,76,129],"adjacent":[35],"to":[37,83,126],"preserve":[38],"semantic":[39,60],"flow.":[40],"Evaluated":[41],"on":[42],"both":[43],"single-hop":[44,68],"multi-hop":[46,91,123],"QA":[47],"datasets,":[48],"our":[49],"approach":[50],"minimal":[53],"(w":[55],"=":[56],"1)":[57],"successfully":[58],"mitigates":[59],"fragmentation":[61],"significantly":[63],"reduces":[64],"token":[65],"consumption.":[66],"On":[67,90],"tasks,":[69,92],"it":[70,115],"achieves":[71],"an":[72,112],"optimal":[73],"compression":[74],"ratio":[75],"27.5x,":[77],"extreme":[79],"configurations":[80],"reaching":[81],"up":[82],"73x":[84],"while":[85,103],"outperforming":[86],"full-document":[88],"baseline.":[89],"provides":[95,111],"highly":[97],"efficient":[98,113],"trade-off,":[99,114],"maintaining":[100],"competitive":[101],"accuracy":[102],"drastically":[104],"cutting":[105],"overhead.":[107],"While":[108],"remains":[116],"slightly":[117],"behind":[118],"full-context":[120],"baseline":[121],"tasks":[124],"due":[125],"complexity":[128],"fact-chaining.":[130]},"counts_by_year":[],"updated_date":"2026-11-08T12:12:28.789561","created_date":"2026-11-04T00:00:00"}