{"id":"https://openalex.org/W7204181747","doi":"https://doi.org/10.1145/3837062.3839371","title":"Evaluating Embedding Models and Preprocessing for Retrieval of MDE Elements in RAG Systems","display_name":"Evaluating Embedding Models and Preprocessing for Retrieval of MDE Elements in RAG Systems","publication_year":2026,"publication_date":"2026-10-04","ids":{"openalex":"https://openalex.org/W7204181747","doi":"https://doi.org/10.1145/3837062.3839371"},"language":"en","primary_location":{"id":"doi:10.1145/3837062.3839371","doi":"https://doi.org/10.1145/3837062.3839371","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3837062.3839371","pdf_url":null,"source":{"id":"https://openalex.org/S7407088064","display_name":"ACM/IEEE International Conference on Model Driven Engineering Languages and Systems (MODELS)","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":"conference"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the ACM/IEEE 29th International Conference on Model Driven Engineering Languages and Systems","raw_type":"proceedings-article"},"volume":null,"type":"conference-paper","indexed_in":["crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://doi.org/10.1145/3837062.3839371","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5138631151","display_name":"Julian Ro\u00dfkothen","orcid":"https://orcid.org/0009-0002-4682-3216","observed_orcids":["https://orcid.org/0009-0002-4682-3216"]},"institutions":[{"id":"https://openalex.org/I102335020","display_name":"Karlsruhe Institute of Technology","ror":"https://ror.org/04t3en479","country_code":"DE","type":"education","lineage":["https://openalex.org/I102335020","https://openalex.org/I1305996414"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Julian Ro\u00dfkothen","raw_affiliation_strings":["Karlsruhe Institute of Technology (KIT), Karlsruhe, Germany and Vector Informatik GmbH, Karlsruhe, Germany"],"raw_orcid":"https://orcid.org/0009-0002-4682-3216","affiliations":[{"raw_affiliation_string":"Karlsruhe Institute of Technology (KIT), Karlsruhe, Germany and Vector Informatik GmbH, Karlsruhe, Germany","institution_ids":["https://openalex.org/I102335020"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5148166229","display_name":"David Inca Pilco","orcid":"https://orcid.org/0009-0007-1063-1745","observed_orcids":["https://orcid.org/0009-0007-1063-1745"]},"institutions":[{"id":"https://openalex.org/I102335020","display_name":"Karlsruhe Institute of Technology","ror":"https://ror.org/04t3en479","country_code":"DE","type":"education","lineage":["https://openalex.org/I102335020","https://openalex.org/I1305996414"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"David Inca Pilco","raw_affiliation_strings":["Karlsruhe Institute of Technology (KIT), Karlsruhe, Germany"],"raw_orcid":"https://orcid.org/0009-0007-1063-1745","affiliations":[{"raw_affiliation_string":"Karlsruhe Institute of Technology (KIT), Karlsruhe, Germany","institution_ids":["https://openalex.org/I102335020"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5036363653","display_name":"Tobias Hey","orcid":"https://orcid.org/0000-0003-0381-1020","observed_orcids":["https://orcid.org/0000-0003-0381-1020"]},"institutions":[{"id":"https://openalex.org/I102335020","display_name":"Karlsruhe Institute of Technology","ror":"https://ror.org/04t3en479","country_code":"DE","type":"education","lineage":["https://openalex.org/I102335020","https://openalex.org/I1305996414"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Tobias Hey","raw_affiliation_strings":["Karlsruhe Institute of Technology (KIT), Karlsruhe, Germany"],"raw_orcid":"https://orcid.org/0000-0003-0381-1020","affiliations":[{"raw_affiliation_string":"Karlsruhe Institute of Technology (KIT), Karlsruhe, Germany","institution_ids":["https://openalex.org/I102335020"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5112230958","display_name":"Clemens Reichmann","orcid":"https://orcid.org/0009-0003-0827-5375","observed_orcids":["https://orcid.org/0009-0003-0827-5375"]},"institutions":[{"id":"https://openalex.org/I4210155650","display_name":"Staatliche Hochschule f\u00fcr Gestaltung Karlsruhe","ror":"https://ror.org/04vq9c111","country_code":"DE","type":"education","lineage":["https://openalex.org/I4210155650"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Clemens Reichmann","raw_affiliation_strings":["Vector Informatik GmbH, Karlsruhe, Germany"],"raw_orcid":"https://orcid.org/0009-0003-0827-5375","affiliations":[{"raw_affiliation_string":"Vector Informatik GmbH, Karlsruhe, Germany","institution_ids":["https://openalex.org/I4210155650"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5033445475","display_name":"Ralf Reussner","orcid":"https://orcid.org/0000-0002-9308-6290","observed_orcids":["https://orcid.org/0000-0002-9308-6290"]},"institutions":[{"id":"https://openalex.org/I102335020","display_name":"Karlsruhe Institute of Technology","ror":"https://ror.org/04t3en479","country_code":"DE","type":"education","lineage":["https://openalex.org/I102335020","https://openalex.org/I1305996414"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Ralf Reussner","raw_affiliation_strings":["Karlsruhe Institute of Technology (KIT), Karlsruhe, Germany"],"raw_orcid":"https://orcid.org/0000-0002-9308-6290","affiliations":[{"raw_affiliation_string":"Karlsruhe Institute of Technology (KIT), Karlsruhe, Germany","institution_ids":["https://openalex.org/I102335020"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.78203349,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"634","last_page":"643"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.6011000275611877,"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":0.6011000275611877,"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/T11450","display_name":"Model-Driven Software Engineering Techniques","score":0.20250000059604645,"subfield":{"id":"https://openalex.org/subfields/1712","display_name":"Software"},"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/T10260","display_name":"Software Engineering Research","score":0.11540000140666962,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/model-driven-engineering","display_name":"model-driven engineering","score":0.8550000190734863},{"id":"https://openalex.org/keywords/retrieval-augmented-generation","display_name":"retrieval-augmented generation","score":0.9309999942779541},{"id":"https://openalex.org/keywords/text-embedding-models","display_name":"text embedding models","score":0.8230000138282776},{"id":"https://openalex.org/keywords/data-preprocessing","display_name":"data preprocessing","score":0.9509999752044678},{"id":"https://openalex.org/keywords/question-answering","display_name":"question answering","score":0.515999972820282}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8235999941825867},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.8015999794006348},{"id":"https://openalex.org/C52723943","wikidata":"https://www.wikidata.org/wiki/Q1127410","display_name":"Serialization","level":2,"score":0.7336999773979187},{"id":"https://openalex.org/C34736171","wikidata":"https://www.wikidata.org/wiki/Q918333","display_name":"Preprocessor","level":2,"score":0.6133000254631042},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.526199996471405},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.48579999804496765},{"id":"https://openalex.org/C67186912","wikidata":"https://www.wikidata.org/wiki/Q367664","display_name":"Data modeling","level":2,"score":0.4422999918460846},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.42649999260902405},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.3871999979019165},{"id":"https://openalex.org/C10551718","wikidata":"https://www.wikidata.org/wiki/Q5227332","display_name":"Data pre-processing","level":2,"score":0.38510000705718994},{"id":"https://openalex.org/C100463513","wikidata":"https://www.wikidata.org/wiki/Q5227322","display_name":"Data model (GIS)","level":2,"score":0.35929998755455017},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.3490999937057495},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.3431999981403351},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.32989999651908875},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3276999890804291},{"id":"https://openalex.org/C509989072","wikidata":"https://www.wikidata.org/wiki/Q15188241","display_name":"Model-driven architecture","level":4,"score":0.304500013589859},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.2831000089645386},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.27410000562667847},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.2639000117778778},{"id":"https://openalex.org/C168167062","wikidata":"https://www.wikidata.org/wiki/Q1117970","display_name":"Component (thermodynamics)","level":2,"score":0.26249998807907104},{"id":"https://openalex.org/C45357846","wikidata":"https://www.wikidata.org/wiki/Q2001982","display_name":"Notation","level":2,"score":0.2551000118255615}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1145/3837062.3839371","doi":"https://doi.org/10.1145/3837062.3839371","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3837062.3839371","pdf_url":null,"source":{"id":"https://openalex.org/S7407088064","display_name":"ACM/IEEE International Conference on Model Driven Engineering Languages and Systems (MODELS)","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":"conference"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the ACM/IEEE 29th International Conference on Model Driven Engineering Languages and Systems","raw_type":"proceedings-article"},{"id":"pmh:oai:EVASTAR-Karlsruhe.de:1000196452","doi":null,"is_oa":true,"landing_page_url":"https://publikationen.bibliothek.kit.edu/1000196452","pdf_url":"https://publikationen.bibliothek.kit.edu/1000196452/188277661","source":{"id":"https://openalex.org/S4306401992","display_name":"Repository KITopen (Karlsruhe Institute of Technology)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I102335020","host_organization_name":"Karlsruhe Institute of Technology","host_organization_lineage":["https://openalex.org/I102335020"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"doc-type:conferenceObject"},{"id":"doi:10.5445/ir/1000196452","doi":"https://doi.org/10.5445/ir/1000196452","is_oa":true,"landing_page_url":"https://doi.org/10.5445/ir/1000196452","pdf_url":null,"source":{"id":"https://openalex.org/S7407052948","display_name":"KITopen","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I102335020","host_organization_name":"Karlsruhe Institute of Technology","host_organization_lineage":["https://openalex.org/I102335020"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"article-journal"}],"best_oa_location":{"id":"doi:10.1145/3837062.3839371","doi":"https://doi.org/10.1145/3837062.3839371","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3837062.3839371","pdf_url":null,"source":{"id":"https://openalex.org/S7407088064","display_name":"ACM/IEEE International Conference on Model Driven Engineering Languages and Systems (MODELS)","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":"conference"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the ACM/IEEE 29th International Conference on Model Driven Engineering Languages and Systems","raw_type":"proceedings-article"},"sustainable_development_goals":[],"sustainable_development_goals_aurora":[{"id":"https://metadata.un.org/sdg/4","display_name":"Quality education","score":0.7386870980262756}],"study_designs":[],"awards":[{"id":"https://openalex.org/G2423332075","display_name":null,"funder_award_id":"SFB1608","funder_id":"https://openalex.org/F4320320879","funder_display_name":"Deutsche Forschungsgemeinschaft"},{"id":"https://openalex.org/G7230842961","display_name":"SFB 1608: Konsistenz in der sichtenbasierten Entwicklung CyberPhysikalischer Systeme","funder_award_id":"501798263","funder_id":"https://openalex.org/F4320320879","funder_display_name":"Deutsche Forschungsgemeinschaft"}],"funders":[{"id":"https://openalex.org/F4320320879","display_name":"Deutsche Forschungsgemeinschaft","ror":"https://ror.org/018mejw64"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Model-driven":[0],"engineering":[1],"tools":[2],"manage":[3],"large,":[4],"interconnected":[5],"models":[6,50,93,103],"that":[7,100],"may":[8],"contain":[9],"millions":[10],"of":[11,47,83,106,110,133],"model":[12,55,84,111,122,129,135,163,170],"elements,":[13],"making":[14],"it":[15],"increasingly":[16],"difficult":[17],"for":[18,34,40,80],"engineers":[19],"to":[20,51,125,168],"locate":[21],"relevant":[22,128],"information":[23],"using":[24,94],"classical":[25],"search":[26],"mechanisms.":[27],"Retrieval-Augmented":[28],"Generation":[29],"is":[30,136],"a":[31,146],"promising":[32],"approach":[33],"enabling":[35],"natural":[36],"language":[37],"question":[38],"answering":[39],"large":[41],"knowledge":[42],"bases,":[43],"but":[44,148],"the":[45,81,108,121,137],"applicability":[46],"text-based":[48],"embedding":[49,70,102,134],"highly":[52],"structured,":[53],"graph-shaped":[54],"artifacts":[56],"has":[57,145],"not":[58],"been":[59],"systematically":[60],"evaluated.":[61],"This":[62],"paper":[63],"presents":[64],"an":[65,87],"empirical":[66],"study":[67],"comparing":[68],"13":[69],"models,":[71],"7":[72,76],"serialization":[73],"formats,":[74],"and":[75,123],"data":[77,142],"preprocessing":[78],"strategies":[79],"retrieval":[82],"elements.":[85,112,130],"In":[86],"evaluation":[88],"on":[89],"two":[90],"PREEvision":[91],"Electric/Electronic-architecture":[92],"automatically":[95],"derived":[96],"questions,":[97],"we":[98],"find":[99,117],"text":[101],"are":[104],"capable":[105],"capturing":[107],"semantics":[109],"However,":[113],"they":[114],"often":[115],"only":[116],"anchor":[118],"points":[119],"in":[120],"struggle":[124],"retrieve":[126],"all":[127],"The":[131],"choice":[132],"dominant":[138],"factor,":[139],"followed":[140],"by":[141],"preprocessing.":[143],"Serialization":[144],"smaller":[147],"model-dependent":[149],"effect;":[150],"compact,":[151],"semi-structured":[152],"formats":[153],"such":[154],"as":[155],"Markdown":[156],"key-value":[157],"pairs":[158],"perform":[159],"most":[160],"robustly.":[161],"Embedding":[162],"retrieval-benchmark":[164],"rankings":[165],"transfer":[166],"well":[167],"structured":[169],"element":[171],"retrieval.":[172]},"counts_by_year":[],"updated_date":"2026-10-07T09:51:55.459714","created_date":"2026-08-26T00:00:00"}