{"id":"https://openalex.org/W4413442564","doi":"https://doi.org/10.1109/coins65080.2025.11125724","title":"The Impact of Chunking Strategies on Domain-Specific Information Retrieval in RAG Systems","display_name":"The Impact of Chunking Strategies on Domain-Specific Information Retrieval in RAG Systems","publication_year":2025,"publication_date":"2025-08-04","ids":{"openalex":"https://openalex.org/W4413442564","doi":"https://doi.org/10.1109/coins65080.2025.11125724"},"language":"en","primary_location":{"id":"doi:10.1109/coins65080.2025.11125724","is_oa":false,"landing_page_url":"https://doi.org/10.1109/coins65080.2025.11125724","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE International Conference on Omni-layer Intelligent Systems (COINS)","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/A5092609840","display_name":"Maximilian St\u00e4bler","orcid":null},"institutions":[{"id":"https://openalex.org/I2898391981","display_name":"Deutsches Zentrum f\u00fcr Luft- und Raumfahrt e. V. (DLR)","ror":"https://ror.org/04bwf3e34","country_code":"DE","type":"facility","lineage":["https://openalex.org/I1305996414","https://openalex.org/I2898391981"]}],"countries":["DE"],"is_corresponding":true,"raw_author_name":"Maximilian St\u00e4bler","raw_affiliation_strings":["German Aerospace Center (DLR),Institute for AI Safety &amp; Security,Ulm,Germany"],"affiliations":[{"raw_affiliation_string":"German Aerospace Center (DLR),Institute for AI Safety &amp; Security,Ulm,Germany","institution_ids":["https://openalex.org/I2898391981"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5109311475","display_name":"Steffen Turnbull","orcid":null},"institutions":[{"id":"https://openalex.org/I4210156774","display_name":"Institut f\u00fcr Arbeitsschutz der Deutschen Gesetzlichen Unfallversicherung","ror":"https://ror.org/0454e9996","country_code":"DE","type":"facility","lineage":["https://openalex.org/I4210156774"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Steffen Turnbull","raw_affiliation_strings":["German Aerospace Center (DLR),Institute for AI Safety &amp; Security,Sankt Augustin,Germany"],"affiliations":[{"raw_affiliation_string":"German Aerospace Center (DLR),Institute for AI Safety &amp; Security,Sankt Augustin,Germany","institution_ids":["https://openalex.org/I4210156774"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100653241","display_name":"Tobias M\u00fcller","orcid":"https://orcid.org/0000-0003-0013-8686"},"institutions":[{"id":"https://openalex.org/I2799978770","display_name":"X-Fab (Germany)","ror":"https://ror.org/030bh9196","country_code":"DE","type":"company","lineage":["https://openalex.org/I2799978770"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Tobias M\u00fcller","raw_affiliation_strings":["Industry-University Collaboration,SAP SE,M&#x00FC;nchen,Germany"],"affiliations":[{"raw_affiliation_string":"Industry-University Collaboration,SAP SE,M&#x00FC;nchen,Germany","institution_ids":["https://openalex.org/I2799978770"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5027628061","display_name":"Chris Langdon","orcid":"https://orcid.org/0000-0002-3043-3806"},"institutions":[{"id":"https://openalex.org/I136722135","display_name":"Claremont Graduate University","ror":"https://ror.org/0157pnt69","country_code":"US","type":"education","lineage":["https://openalex.org/I136722135"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Chris Langdon","raw_affiliation_strings":["Claremont Graduate University,Drucker School of Business,Claremont,USA"],"affiliations":[{"raw_affiliation_string":"Claremont Graduate University,Drucker School of Business,Claremont,USA","institution_ids":["https://openalex.org/I136722135"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5082490608","display_name":"Jorge Marx\u2010G\u00f3mez","orcid":null},"institutions":[{"id":"https://openalex.org/I129877168","display_name":"Carl von Ossietzky Universit\u00e4t Oldenburg","ror":"https://ror.org/033n9gh91","country_code":"DE","type":"education","lineage":["https://openalex.org/I129877168"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Jorge Marx-Gom\u00e9z","raw_affiliation_strings":["University of Oldenburg,Deptarment of Business Informatics,Oldeburg,Germany"],"affiliations":[{"raw_affiliation_string":"University of Oldenburg,Deptarment of Business Informatics,Oldeburg,Germany","institution_ids":["https://openalex.org/I129877168"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5073402824","display_name":"Frank K\u00f6ster","orcid":"https://orcid.org/0000-0001-8684-3698"},"institutions":[{"id":"https://openalex.org/I4210156774","display_name":"Institut f\u00fcr Arbeitsschutz der Deutschen Gesetzlichen Unfallversicherung","ror":"https://ror.org/0454e9996","country_code":"DE","type":"facility","lineage":["https://openalex.org/I4210156774"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Frank K\u00f6ster","raw_affiliation_strings":["German Aerospace Center (DLR),Institute for AI Safety &amp; Security,Sankt Augustin,Germany"],"affiliations":[{"raw_affiliation_string":"German Aerospace Center (DLR),Institute for AI Safety &amp; Security,Sankt Augustin,Germany","institution_ids":["https://openalex.org/I4210156774"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5092609840"],"corresponding_institution_ids":["https://openalex.org/I2898391981"],"apc_list":null,"apc_paid":null,"fwci":12.4244,"has_fulltext":false,"cited_by_count":5,"citation_normalized_percentile":{"value":0.98381712,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":91,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"6"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.9621000289916992,"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":0.9621000289916992,"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/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.9412999749183655,"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/T11269","display_name":"Algorithms and Data Compression","score":0.9370999932289124,"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/computer-science","display_name":"Computer science","score":0.8097645044326782},{"id":"https://openalex.org/keywords/chunking","display_name":"Chunking (psychology)","score":0.7716450691223145},{"id":"https://openalex.org/keywords/domain","display_name":"Domain (mathematical analysis)","score":0.5663787722587585},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.44309112429618835},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3926827311515808},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.3767053186893463},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.07124891877174377}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8097645044326782},{"id":"https://openalex.org/C203357204","wikidata":"https://www.wikidata.org/wiki/Q1089605","display_name":"Chunking (psychology)","level":2,"score":0.7716450691223145},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.5663787722587585},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.44309112429618835},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3926827311515808},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3767053186893463},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.07124891877174377},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/coins65080.2025.11125724","is_oa":false,"landing_page_url":"https://doi.org/10.1109/coins65080.2025.11125724","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE International Conference on Omni-layer Intelligent Systems (COINS)","raw_type":"proceedings-article"},{"id":"pmh:oai:elib.dlr.de:221921","is_oa":false,"landing_page_url":"https://doi.org/10.1109/COINS65080.2025.11125724>.","pdf_url":null,"source":{"id":"https://openalex.org/S4377196266","display_name":"elib (German Aerospace Center)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I2898391981","host_organization_name":"Deutsches Zentrum f\u00fcr Luft- und Raumfahrt e. V. (DLR)","host_organization_lineage":["https://openalex.org/I2898391981"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"acceptedVersion","is_accepted":true,"is_published":false,"raw_source_name":null,"raw_type":"PeerReviewed"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":13,"referenced_works":["https://openalex.org/W3027879771","https://openalex.org/W4386576685","https://openalex.org/W4389519872","https://openalex.org/W4391709255","https://openalex.org/W4393299232","https://openalex.org/W4399597924","https://openalex.org/W4401024187","https://openalex.org/W4401857375","https://openalex.org/W4403111891","https://openalex.org/W4403560390","https://openalex.org/W4404509535","https://openalex.org/W4408581964","https://openalex.org/W4411113004"],"related_works":["https://openalex.org/W2384729545","https://openalex.org/W2198395236","https://openalex.org/W2800417007","https://openalex.org/W147604216","https://openalex.org/W2161080928","https://openalex.org/W4245487161","https://openalex.org/W2090755435","https://openalex.org/W2039036070","https://openalex.org/W2153813398","https://openalex.org/W3204019825"],"abstract_inverted_index":{"We":[0],"benchmark":[1],"90":[2],"chunker\u2013model":[3],"configurations":[4],"across":[5],"seven":[6,40],"arXiv":[7],"domains":[8],"(2520":[9],"retrieval":[10,54],"runs)":[11],"and":[12,22,46,56,84,109],"show":[13],"that":[14,65,106],"a":[15,19],"sentence-based":[16],"splitter":[17],"with":[18,44,98],"512-token":[20],"window":[21],"200-token":[23],"overlap":[24],"reaches":[25],"the":[26],"highest":[27],"token-level":[28],"Intersection-over-Union":[29],"(IoU":[30],"\u2248":[31],"0.099)":[32],"while":[33],"remaining":[34],"compute-efficient.":[35],"Our":[36],"study":[37],"systematically":[38],"pairs":[39],"open-source":[41],"embedding":[42],"models":[43],"semantic":[45],"fixed-size":[47],"chunking":[48],"strategies,":[49],"measuring":[50],"their":[51],"impact":[52],"on":[53],"quality":[55],"latency":[57],"in":[58],"Retrieval-Augmented":[59],"Generation":[60],"(RAG)":[61],"pipelines.":[62],"Results":[63],"reveal":[64],"(i)":[66],"sentence":[67],"splitting":[68],"consistently":[69],"outperforms":[70],"alternative":[71],"heuristics,":[72],"(ii)":[73],"smaller":[74],"embeddings":[75],"deliver":[76],"more":[77],"stable":[78],"cross-domain":[79],"performance":[80],"than":[81],"larger":[82],"ones,":[83],"(iii)":[85],"finance":[86],"texts":[87],"benefit":[88],"most,":[89],"whereas":[90],"astrophysics":[91],"lags.":[92],"The":[93],"accompanying":[94],"code":[95],"provides":[96],"practitioners":[97],"empirically":[99],"grounded":[100],"guidelines":[101],"for":[102],"selecting":[103],"chunking\u2013embedding":[104],"combinations":[105],"balance":[107],"accuracy":[108],"efficiency.":[110]},"counts_by_year":[{"year":2026,"cited_by_count":4},{"year":2025,"cited_by_count":1}],"updated_date":"2026-03-29T08:15:47.926485","created_date":"2025-10-10T00:00:00"}
