{"id":"https://openalex.org/W7154380978","doi":"https://doi.org/10.48550/arxiv.2604.09868","title":"Exploring Structural Complexity in Normative RAG with Graph-based approaches: A case study on the ETSI Standards","display_name":"Exploring Structural Complexity in Normative RAG with Graph-based approaches: A case study on the ETSI Standards","publication_year":2026,"publication_date":"2026-01-31","ids":{"openalex":"https://openalex.org/W7154380978","doi":"https://doi.org/10.48550/arxiv.2604.09868"},"language":null,"primary_location":{"id":"doi:10.48550/arxiv.2604.09868","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2604.09868","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,"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":"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"},"type":"preprint","indexed_in":["datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://doi.org/10.48550/arxiv.2604.09868","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5133618284","display_name":"Aiman Al Masoud","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Masoud, Aiman Al","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5059446425","display_name":"Marco Arazzi","orcid":"https://orcid.org/0000-0002-3371-307X"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Arazzi, Marco","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5052574690","display_name":"S. Germani","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Germani, Simone","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5085793134","display_name":"Antonino Nocera","orcid":"https://orcid.org/0000-0003-2120-2341"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Nocera, Antonino","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":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/T11273","display_name":"Advanced Graph Neural Networks","score":0.45249998569488525,"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/T11273","display_name":"Advanced Graph Neural Networks","score":0.45249998569488525,"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/T10856","display_name":"Intellectual Property and Patents","score":0.11159999668598175,"subfield":{"id":"https://openalex.org/subfields/1405","display_name":"Management of Technology and Innovation"},"field":{"id":"https://openalex.org/fields/14","display_name":"Business, Management and Accounting"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T11550","display_name":"Text and Document Classification Technologies","score":0.09629999846220016,"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/normative","display_name":"Normative","score":0.5799999833106995},{"id":"https://openalex.org/keywords/search-engine-indexing","display_name":"Search engine indexing","score":0.5024999976158142},{"id":"https://openalex.org/keywords/focus","display_name":"Focus (optics)","score":0.4814999997615814},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.4715999960899353},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.4571000039577484},{"id":"https://openalex.org/keywords/graph","display_name":"Graph","score":0.4133000075817108},{"id":"https://openalex.org/keywords/relevance","display_name":"Relevance (law)","score":0.39070001244544983}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7788000106811523},{"id":"https://openalex.org/C44725695","wikidata":"https://www.wikidata.org/wiki/Q288156","display_name":"Normative","level":2,"score":0.5799999833106995},{"id":"https://openalex.org/C75165309","wikidata":"https://www.wikidata.org/wiki/Q2258979","display_name":"Search engine indexing","level":2,"score":0.5024999976158142},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.4814999997615814},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.4749000072479248},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.4715999960899353},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.4571000039577484},{"id":"https://openalex.org/C132525143","wikidata":"https://www.wikidata.org/wiki/Q141488","display_name":"Graph","level":2,"score":0.4133000075817108},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4133000075817108},{"id":"https://openalex.org/C158154518","wikidata":"https://www.wikidata.org/wiki/Q7310970","display_name":"Relevance (law)","level":2,"score":0.39070001244544983},{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.3646000027656555},{"id":"https://openalex.org/C170133592","wikidata":"https://www.wikidata.org/wiki/Q1806883","display_name":"Latent semantic analysis","level":2,"score":0.3352999985218048},{"id":"https://openalex.org/C77618280","wikidata":"https://www.wikidata.org/wiki/Q1155772","display_name":"Scheme (mathematics)","level":2,"score":0.289000004529953},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.289000004529953},{"id":"https://openalex.org/C166052673","wikidata":"https://www.wikidata.org/wiki/Q83021","display_name":"Empirical evidence","level":2,"score":0.289000004529953},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.2768999934196472},{"id":"https://openalex.org/C120936955","wikidata":"https://www.wikidata.org/wiki/Q2155640","display_name":"Empirical research","level":2,"score":0.2741999924182892},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.26759999990463257},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.2662999927997589},{"id":"https://openalex.org/C171686336","wikidata":"https://www.wikidata.org/wiki/Q3532085","display_name":"Topic model","level":2,"score":0.26460000872612}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2604.09868","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2604.09868","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,"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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"doi:10.48550/arxiv.2604.09868","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2604.09868","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,"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":"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":[{"score":0.43799325823783875,"id":"https://metadata.un.org/sdg/9","display_name":"Industry, innovation and infrastructure"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Industrial":[0],"standards":[1,155,245],"and":[2,11,51,77,151,156,183,222,244],"normative":[3,56,243],"documents":[4],"exhibit":[5],"intricate":[6],"hierarchical":[7],"structures,":[8],"domain-specific":[9],"lexicons,":[10],"extensive":[12],"cross-referential":[13],"dependencies,":[14],"which":[15,89,124],"making":[16],"it":[17],"challenging":[18],"to":[19,37,46,123,134,147,160,187,232],"process":[20],"them":[21],"directly":[22,191],"by":[23],"Large":[24],"Language":[25],"Models":[26],"(LLMs).":[27],"While":[28],"Retrieval-Augmented":[29],"Generation":[30],"(RAG)":[31],"provides":[32],"a":[33,102,117,142,203,209,238],"computationally":[34],"efficient":[35],"alternative":[36],"LLM":[38],"fine-tuning,":[39],"standard":[40],"\"vanilla\"":[41],"vector-based":[42],"retrieval":[43,106,194,235],"may":[44],"fail":[45],"capture":[47],"the":[48,59,65,83,109,126,148,173,193,218,226],"latent":[49],"structural":[50,221],"relational":[52],"features":[53],"intrinsic":[54],"in":[55],"documents.":[57,158],"With":[58],"objective":[60],"of":[61,85,111,119,154,220],"shedding":[62],"light":[63],"on":[64,167],"most":[66],"promising":[67],"technique":[68],"for":[69,74,130,241],"building":[70],"high-performance":[71],"RAG":[72,87,144],"solutions":[73],"normative,":[75],"standards,":[76,170],"regulatory":[78,157],"documents,":[79],"this":[80,137],"paper":[81],"investigates":[82],"efficacy":[84],"Graph":[86],"architectures,":[88],"represent":[90],"information":[91,224],"as":[92,122,172],"interconnected":[93],"nodes,":[94],"thus":[95],"moving":[96],"from":[97],"simple":[98],"semantic":[99],"similarity":[100],"toward":[101],"more":[103],"robust,":[104],"relation-aware":[105],"mechanism.":[107],"Despite":[108],"promise":[110],"graph-based":[112],"techniques,":[113],"there":[114],"is":[115,125],"currently":[116],"lack":[118],"empirical":[120],"evidence":[121],"optimal":[127],"indexing":[128],"strategy":[129],"technical":[131],"standards.":[132],"Therefore,":[133],"help":[135],"solve":[136],"knowledge":[138],"gap,":[139],"we":[140,165],"propose":[141],"specialized":[143],"methodology":[145],"tailored":[146],"unique":[149],"structure":[150,190],"lexical":[152,223],"characteristics":[153],"Moreover,":[159],"keep":[161],"our":[162],"investigation":[163],"grounded,":[164],"focus":[166],"well-known":[168],"public":[169],"such":[171],"ETSI":[174],"EN":[175],"301":[176],"489":[177],"series.":[178],"We":[179],"evaluate":[180],"several":[181],"lightweight":[182],"low-latency":[184],"strategies":[185],"designed":[186],"embed":[188],"document":[189],"into":[192,225],"workflow.":[195],"The":[196],"considered":[197],"approaches":[198],"are":[199],"rigorously":[200],"tested":[201],"against":[202],"custom":[204],"synthesized":[205],"Q&A":[206],"dataset,":[207],"facilitating":[208],"quantitative":[210],"performance":[211],"analysis.":[212],"Our":[213],"experimental":[214],"results":[215],"demonstrate":[216],"that":[217],"incorporation":[219],"index":[227],"can":[228],"enhance,":[229],"at":[230],"least":[231],"some":[233],"extent,":[234],"performance,":[236],"providing":[237],"scalable":[239],"framework":[240],"automated":[242],"elaboration.":[246]},"counts_by_year":[],"updated_date":"2026-07-28T07:46:37.118299","created_date":"2026-04-15T00:00:00"}