{"id":"https://openalex.org/W7147690272","doi":"https://doi.org/10.1109/icaiic68212.2026.11454314","title":"Empirical Analysis of Text Segmentation for Statute-Level Retrieval in Regulatory RAG Pipelines","display_name":"Empirical Analysis of Text Segmentation for Statute-Level Retrieval in Regulatory RAG Pipelines","publication_year":2026,"publication_date":"2026-02-24","ids":{"openalex":"https://openalex.org/W7147690272","doi":"https://doi.org/10.1109/icaiic68212.2026.11454314"},"language":null,"primary_location":{"id":"doi:10.1109/icaiic68212.2026.11454314","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icaiic68212.2026.11454314","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2026 International Conference on Artificial Intelligence in Information and Communication (ICAIIC)","raw_type":"proceedings-article"},"type":"article","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/A5100642851","display_name":"Byung\u2010Soo Kim","orcid":"https://orcid.org/0000-0001-5210-7430"},"institutions":[{"id":"https://openalex.org/I104338594","display_name":"Inje University","ror":"https://ror.org/04xqwq985","country_code":"KR","type":"education","lineage":["https://openalex.org/I104338594"]}],"countries":["KR"],"is_corresponding":true,"raw_author_name":"Beomseok Kim","raw_affiliation_strings":["Inje University,Dept. of Medical IT,Gimhae,South Korea"],"affiliations":[{"raw_affiliation_string":"Inje University,Dept. of Medical IT,Gimhae,South Korea","institution_ids":["https://openalex.org/I104338594"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5043867326","display_name":"Hoansuk Choi","orcid":null},"institutions":[{"id":"https://openalex.org/I71007489","display_name":"Kyungnam University","ror":"https://ror.org/037pkxm09","country_code":"KR","type":"education","lineage":["https://openalex.org/I71007489"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Hoansuk Choi","raw_affiliation_strings":["Kyungnam University,Dept. of Game Engineering,Changwon,South Korea"],"affiliations":[{"raw_affiliation_string":"Kyungnam University,Dept. of Game Engineering,Changwon,South Korea","institution_ids":["https://openalex.org/I71007489"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5125636932","display_name":"Namhyun Yoo","orcid":null},"institutions":[{"id":"https://openalex.org/I104338594","display_name":"Inje University","ror":"https://ror.org/04xqwq985","country_code":"KR","type":"education","lineage":["https://openalex.org/I104338594"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Namhyun Yoo","raw_affiliation_strings":["Inje University,Dept. of Computer Engineering,Gimhae,South Korea"],"affiliations":[{"raw_affiliation_string":"Inje University,Dept. of Computer Engineering,Gimhae,South Korea","institution_ids":["https://openalex.org/I104338594"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5114860745","display_name":"Jinhong Yang","orcid":"https://orcid.org/0000-0002-7756-0263"},"institutions":[{"id":"https://openalex.org/I104338594","display_name":"Inje University","ror":"https://ror.org/04xqwq985","country_code":"KR","type":"education","lineage":["https://openalex.org/I104338594"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Jinhong Yang","raw_affiliation_strings":["Inje University,Dept. of Medical IT,Gimhae,South Korea"],"affiliations":[{"raw_affiliation_string":"Inje University,Dept. of Medical IT,Gimhae,South Korea","institution_ids":["https://openalex.org/I104338594"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5100642851"],"corresponding_institution_ids":["https://openalex.org/I104338594"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.90415358,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1204","last_page":"1209"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.703000009059906,"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":0.703000009059906,"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/T11710","display_name":"Biomedical Text Mining and Ontologies","score":0.052799999713897705,"subfield":{"id":"https://openalex.org/subfields/1312","display_name":"Molecular Biology"},"field":{"id":"https://openalex.org/fields/13","display_name":"Biochemistry, Genetics and Molecular Biology"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}},{"id":"https://openalex.org/T10286","display_name":"Information Retrieval and Search Behavior","score":0.04439999908208847,"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/chunking","display_name":"Chunking (psychology)","score":0.7457000017166138},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.40310001373291016},{"id":"https://openalex.org/keywords/hierarchy","display_name":"Hierarchy","score":0.38940000534057617},{"id":"https://openalex.org/keywords/precision-and-recall","display_name":"Precision and recall","score":0.3808000087738037},{"id":"https://openalex.org/keywords/domain","display_name":"Domain (mathematical analysis)","score":0.3416999876499176},{"id":"https://openalex.org/keywords/data-retrieval","display_name":"Data retrieval","score":0.335999995470047},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.3255999982357025},{"id":"https://openalex.org/keywords/mean-reciprocal-rank","display_name":"Mean reciprocal rank","score":0.3019999861717224}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7771999835968018},{"id":"https://openalex.org/C203357204","wikidata":"https://www.wikidata.org/wiki/Q1089605","display_name":"Chunking (psychology)","level":2,"score":0.7457000017166138},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4693000018596649},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.45089998841285706},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.40310001373291016},{"id":"https://openalex.org/C31170391","wikidata":"https://www.wikidata.org/wiki/Q188619","display_name":"Hierarchy","level":2,"score":0.38940000534057617},{"id":"https://openalex.org/C81669768","wikidata":"https://www.wikidata.org/wiki/Q2359161","display_name":"Precision and recall","level":2,"score":0.3808000087738037},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.3416999876499176},{"id":"https://openalex.org/C551230270","wikidata":"https://www.wikidata.org/wiki/Q4368942","display_name":"Data retrieval","level":2,"score":0.335999995470047},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.3255999982357025},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3249000012874603},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.3221000134944916},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.31690001487731934},{"id":"https://openalex.org/C44083865","wikidata":"https://www.wikidata.org/wiki/Q3853443","display_name":"Mean reciprocal rank","level":2,"score":0.3019999861717224},{"id":"https://openalex.org/C161156560","wikidata":"https://www.wikidata.org/wiki/Q1638872","display_name":"Document retrieval","level":2,"score":0.30149999260902405},{"id":"https://openalex.org/C164226766","wikidata":"https://www.wikidata.org/wiki/Q7293202","display_name":"Rank (graph theory)","level":2,"score":0.2973000109195709},{"id":"https://openalex.org/C120936955","wikidata":"https://www.wikidata.org/wiki/Q2155640","display_name":"Empirical research","level":2,"score":0.2906999886035919},{"id":"https://openalex.org/C75949130","wikidata":"https://www.wikidata.org/wiki/Q848010","display_name":"Database transaction","level":2,"score":0.2890999913215637},{"id":"https://openalex.org/C2780801425","wikidata":"https://www.wikidata.org/wiki/Q5164392","display_name":"Construct (python library)","level":2,"score":0.28519999980926514},{"id":"https://openalex.org/C152124472","wikidata":"https://www.wikidata.org/wiki/Q1204361","display_name":"Redundancy (engineering)","level":2,"score":0.26750001311302185},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.26260000467300415},{"id":"https://openalex.org/C2474386","wikidata":"https://www.wikidata.org/wiki/Q461183","display_name":"Text corpus","level":2,"score":0.25999999046325684},{"id":"https://openalex.org/C482391","wikidata":"https://www.wikidata.org/wiki/Q101244","display_name":"Acronym","level":2,"score":0.25920000672340393},{"id":"https://openalex.org/C125411270","wikidata":"https://www.wikidata.org/wiki/Q18653","display_name":"Encoding (memory)","level":2,"score":0.25920000672340393},{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.25279998779296875}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icaiic68212.2026.11454314","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icaiic68212.2026.11454314","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2026 International Conference on Artificial Intelligence in Information and Communication (ICAIIC)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/16","display_name":"Peace, Justice and strong institutions","score":0.5196648836135864}],"awards":[{"id":"https://openalex.org/G8410008605","display_name":null,"funder_award_id":"IITP-2025-RS-2024-00436773","funder_id":"https://openalex.org/F4320322086","funder_display_name":"Korea Research Institute for Human Settlements"}],"funders":[{"id":"https://openalex.org/F4320322086","display_name":"Korea Research Institute for Human Settlements","ror":"https://ror.org/05kf6ye97"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":8,"referenced_works":["https://openalex.org/W4381568928","https://openalex.org/W4386566622","https://openalex.org/W4408145721","https://openalex.org/W4408323770","https://openalex.org/W4409716856","https://openalex.org/W4411120464","https://openalex.org/W4416379250","https://openalex.org/W7117144337"],"related_works":[],"abstract_inverted_index":{"Retrieval-Augmented":[0],"Generation":[1],"(RAG)":[2],"is":[3],"increasingly":[4],"adopted":[5],"in":[6,133,170,185,214],"the":[7,24,37,61,74,122,153,158,208],"legal":[8,28,65,148,212],"domain":[9],"to":[10,31,118,130,162],"mitigate":[11],"hallucinations":[12],"and":[13,51,83,89,98,203],"ensure":[14,163],"regulatory":[15],"compliance.":[16],"However,":[17],"standard":[18],"fixed-size":[19,47],"chunking":[20,40,48,57,195],"strategies":[21,41,132],"often":[22],"disrupt":[23],"logical":[25],"hierarchy":[26,63],"of":[27,39,64,80,210],"texts,":[29],"leading":[30],"context":[32],"fragmentation.":[33],"This":[34],"paper":[35],"investigates":[36],"impact":[38],"on":[42,60],"retrieval":[43,85,101,127,135,183,201],"performance":[44,86,107,128],"by":[45],"comparing":[46],"(256,":[49],"512,":[50],"1024":[52],"tokens)":[53,113],"with":[54],"a":[55,70,106,141,171,197],"structure-aware":[56,124,194],"method":[58,125],"based":[59],"inherent":[62],"articles":[66],"(Article-Paragraph-Subparagraph).":[67],"We":[68],"construct":[69],"synthetic":[71],"dataset":[72],"using":[73,87],"Personal":[75],"Information":[76],"Protection":[77],"Act":[78],"(PIPA)":[79],"South":[81],"Korea":[82],"evaluate":[84],"Hit@k":[88],"Mean":[90],"Reciprocal":[91],"Rank":[92],"(MRR)":[93],"under":[94],"both":[95],"lexical":[96],"(BM25)":[97],"semantic":[99,134,204],"(dense)":[100],"settings.":[102],"Experimental":[103],"results":[104,167],"reveal":[105],"inversion:":[108],"smaller":[109],"fixed":[110],"chunks":[111],"(256":[112],"benefit":[114],"keyword-based":[115],"search":[116],"due":[117],"length":[119],"bias,":[120],"while":[121,145],"proposed":[123],"achieves":[126],"comparable":[129],"large-context":[131],"(MRR":[136],"0.737":[137],"vs.":[138],"0.736,":[139],"i.e.,":[140],"numerically":[142],"small":[143],"difference)":[144],"preserving":[146],"complete":[147],"provisions.":[149],"Furthermore,":[150],"we":[151],"detail":[152],"specific":[154],"experimental":[155],"environment,":[156],"including":[157],"klue/roberta-base":[159],"model":[160],"configuration,":[161],"reproducibility.":[164],"Although":[165],"these":[166],"are":[168],"obtained":[169],"single-statute,":[172],"retrieval-only":[173],"setting,":[174],"they":[175],"provide":[176],"an":[177],"initial":[178],"empirical":[179],"basis":[180],"for":[181],"designing":[182],"components":[184],"statute-level":[186,215],"RAG":[187,216],"pipelines.":[188],"Overall,":[189],"our":[190],"findings":[191],"suggest":[192],"that":[193],"offers":[196],"promising":[198],"trade-off":[199],"between":[200],"precision":[202],"completeness,":[205],"helping":[206],"minimize":[207],"risk":[209],"fragmented":[211],"contexts":[213],"systems.":[217]},"counts_by_year":[],"updated_date":"2026-04-09T08:11:56.329763","created_date":"2026-04-02T00:00:00"}