{"id":"https://openalex.org/W7225798308","doi":"https://doi.org/10.5281/zenodo.24130102","title":"A Curated Keyword Store as a Complement to RAG for Closed-Domain Question Answering","display_name":"A Curated Keyword Store as a Complement to RAG for Closed-Domain Question Answering","publication_year":2026,"publication_date":"2026-11-11","ids":{"openalex":"https://openalex.org/W7225798308","doi":"https://doi.org/10.5281/zenodo.24130102"},"language":"en","primary_location":{"id":"doi:10.5281/zenodo.24130102","doi":"https://doi.org/10.5281/zenodo.24130102","is_oa":true,"landing_page_url":"https://doi.org/10.5281/zenodo.24130102","pdf_url":null,"source":{"id":"https://openalex.org/S4306400562","display_name":"Zenodo (CERN European Organization for Nuclear Research)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I67311998","host_organization_name":"European Organization for Nuclear Research","host_organization_lineage":["https://openalex.org/I67311998"],"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"},"volume":null,"type":"preprint","is_traditional":true,"indexed_in":["datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://doi.org/10.5281/zenodo.24130102","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5161494066","display_name":"Arnav Eluri","orcid":"https://orcid.org/0009-0008-8282-392X","observed_orcids":["https://orcid.org/0009-0008-8282-392X"]},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Arnav Eluri","raw_affiliation_strings":[],"raw_orcid":"https://orcid.org/0009-0008-8282-392X","affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":["https://openalex.org/A5161494066"],"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/T10286","display_name":"Information Retrieval and Search Behavior","score":0.5990999937057495,"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"}},"topics":[{"id":"https://openalex.org/T10286","display_name":"Information Retrieval and Search Behavior","score":0.5990999937057495,"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/T10028","display_name":"Topic Modeling","score":0.3889000117778778,"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":0.003000000026077032,"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":[],"concepts":[{"id":"https://openalex.org/C112313634","wikidata":"https://www.wikidata.org/wiki/Q7886648","display_name":"Complement (music)","level":5,"score":0.7451000213623047},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7084000110626221},{"id":"https://openalex.org/C2779662365","wikidata":"https://www.wikidata.org/wiki/Q5416694","display_name":"Event (particle physics)","level":2,"score":0.6377999782562256},{"id":"https://openalex.org/C2777601683","wikidata":"https://www.wikidata.org/wiki/Q6499736","display_name":"Vocabulary","level":2,"score":0.6225000023841858},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.6065999865531921},{"id":"https://openalex.org/C44291984","wikidata":"https://www.wikidata.org/wiki/Q1074173","display_name":"Question answering","level":2,"score":0.54339998960495},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.4814000129699707},{"id":"https://openalex.org/C87619178","wikidata":"https://www.wikidata.org/wiki/Q126002","display_name":"Concatenation (mathematics)","level":2,"score":0.4756999909877777},{"id":"https://openalex.org/C74172769","wikidata":"https://www.wikidata.org/wiki/Q1446839","display_name":"Routing (electronic design automation)","level":2,"score":0.4357999861240387},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4323999881744385},{"id":"https://openalex.org/C2778572836","wikidata":"https://www.wikidata.org/wiki/Q380933","display_name":"Space (punctuation)","level":2,"score":0.4260999858379364},{"id":"https://openalex.org/C201280247","wikidata":"https://www.wikidata.org/wiki/Q11032","display_name":"Newspaper","level":2,"score":0.4187000095844269},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3652999997138977},{"id":"https://openalex.org/C43521106","wikidata":"https://www.wikidata.org/wiki/Q2165493","display_name":"Pipeline (software)","level":2,"score":0.3560999929904938},{"id":"https://openalex.org/C2779227376","wikidata":"https://www.wikidata.org/wiki/Q6505497","display_name":"Layer (electronics)","level":2,"score":0.351500004529953},{"id":"https://openalex.org/C123657996","wikidata":"https://www.wikidata.org/wiki/Q12271","display_name":"Architecture","level":2,"score":0.34150001406669617},{"id":"https://openalex.org/C77618280","wikidata":"https://www.wikidata.org/wiki/Q1155772","display_name":"Scheme (mathematics)","level":2,"score":0.3034000098705292},{"id":"https://openalex.org/C2780154230","wikidata":"https://www.wikidata.org/wiki/Q513420","display_name":"Undo","level":2,"score":0.2948000133037567},{"id":"https://openalex.org/C75165309","wikidata":"https://www.wikidata.org/wiki/Q2258979","display_name":"Search engine indexing","level":2,"score":0.27149999141693115},{"id":"https://openalex.org/C94966114","wikidata":"https://www.wikidata.org/wiki/Q29256","display_name":"Black box","level":2,"score":0.2655999958515167},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.26269999146461487}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.5281/zenodo.24130102","doi":"https://doi.org/10.5281/zenodo.24130102","is_oa":true,"landing_page_url":"https://doi.org/10.5281/zenodo.24130102","pdf_url":null,"source":{"id":"https://openalex.org/S4306400562","display_name":"Zenodo (CERN European Organization for Nuclear Research)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I67311998","host_organization_name":"European Organization for Nuclear Research","host_organization_lineage":["https://openalex.org/I67311998"],"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"},{"id":"doi:10.5281/zenodo.24130103","doi":"https://doi.org/10.5281/zenodo.24130103","is_oa":true,"landing_page_url":"https://doi.org/10.5281/zenodo.24130103","pdf_url":null,"source":{"id":"https://openalex.org/S4306400562","display_name":"Zenodo (CERN European Organization for Nuclear Research)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I67311998","host_organization_name":"European Organization for Nuclear Research","host_organization_lineage":["https://openalex.org/I67311998"],"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":"doi:10.5281/zenodo.24130102","doi":"https://doi.org/10.5281/zenodo.24130102","is_oa":true,"landing_page_url":"https://doi.org/10.5281/zenodo.24130102","pdf_url":null,"source":{"id":"https://openalex.org/S4306400562","display_name":"Zenodo (CERN European Organization for Nuclear Research)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I67311998","host_organization_name":"European Organization for Nuclear Research","host_organization_lineage":["https://openalex.org/I67311998"],"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"},"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":[],"abstract_inverted_index":{"Topical":[0],"noise":[1,12],"is":[2,20,51,94,100,168,174,185],"added":[3],"by":[4],"the":[5,17,60,63,105,114,166,169,181],"dense-vector":[6],"retrieval":[7,30,50],"of":[8,34,46,117,183],"RAG":[9,103,145],"systems.":[10],"That":[11],"can":[13],"be":[14],"avoided,":[15],"when":[16,96],"knowledge":[18],"space":[19],"small,":[21],"and":[22,44,99,125,149,175],"maintained":[23],"actively!":[24],"The":[25,49,139,163],"Curated":[26],"Knowledge":[27],"Store":[28],"(CKS):":[29],"layer":[31],"designed":[32],"out":[33,71],"Markdown":[35],"file":[36],"with":[37],"explicit":[38],"routing":[39],"to":[40,59,102,121,171],"keywords,":[41],"human-verified":[42],"flags":[43],"cases":[45],"staleness":[47],"date.":[48],"deterministic,":[52],"that":[53,62,77,92,107],"is,":[54],"it":[55,67,75,108],"will":[56],"either":[57],"conform":[58],"vocabulary":[61,84],"query":[64],"declares":[65],"or":[66],"won't.":[68],"This":[69],"clears":[70],"partial-match":[72],"noise,":[73],"but":[74,160,178],"means":[76],"no":[78],"words":[79],"are":[80],"recalled":[81],"on":[82],"a":[83,87,127],"gap.":[85],"With":[86],"CKS-first":[88],"/":[89],"RAG-fallback":[90],"hybrid,":[91],"accuracy":[93,182],"leveraged":[95],"that's":[97],"available,":[98],"rerouted":[101],"in":[104],"event":[106],"isn't.":[109],"We":[110],"outline":[111],"design,":[112],"analyse":[113],"PT":[115],"curve":[116],"our":[118],"design":[119],"compared":[120],"BM25,":[122],"dense":[123],"retrieval,":[124],"present":[126],"small":[128],"feasibility":[129],"study":[130],"using":[131],"ten":[132],"factoid":[133],"questions":[134],"from":[135],"one":[136],"newspaper":[137],"edition.":[138],"concatenation":[140],"hybrid":[141],"achieved":[142,147,152],"8.7/10,":[143],"whereas":[144],"alone":[146,151],"8.0/10,":[148],"CKS":[150],"4.5/10.":[153],"These":[154],"figures":[155],"do":[156],"not":[157,179],"represent":[158],"actual,":[159],"indicative,":[161],"figures.":[162],"principle":[164],"behind":[165],"architecture":[167],"ability":[170],"show":[172],"what":[173,184],"isn't":[176],"happening,":[177],"necessarily":[180],"happening.":[186]},"counts_by_year":[],"updated_date":"2026-11-12T12:28:57.059296","created_date":"2026-11-12T00:00:00"}
