{"id":"https://openalex.org/W4411113004","doi":"https://doi.org/10.18653/v1/2025.findings-naacl.114","title":"Is Semantic Chunking Worth the Computational Cost?","display_name":"Is Semantic Chunking Worth the Computational Cost?","publication_year":2025,"publication_date":"2025-01-01","ids":{"openalex":"https://openalex.org/W4411113004","doi":"https://doi.org/10.18653/v1/2025.findings-naacl.114"},"language":"en","primary_location":{"id":"doi:10.18653/v1/2025.findings-naacl.114","doi":"https://doi.org/10.18653/v1/2025.findings-naacl.114","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.findings-naacl.114","pdf_url":"https://aclanthology.org/2025.findings-naacl.114.pdf","source":{"id":"https://openalex.org/S4363605604","display_name":"Findings of the Association for Computational Linguistics: NAACL","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":"Findings of the Association for Computational Linguistics: NAACL 2025","raw_type":"proceedings-article"},"volume":null,"type":"conference-paper","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://aclanthology.org/2025.findings-naacl.114.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5102590261","display_name":"Renyi Qu","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Renyi Qu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102841872","display_name":"Ruixuan Tu","orcid":"https://orcid.org/0000-0001-7610-4138","observed_orcids":["https://orcid.org/0000-0001-7610-4138"]},"institutions":[{"id":"https://openalex.org/I135310074","display_name":"University of Wisconsin\u2013Madison","ror":"https://ror.org/01y2jtd41","country_code":"US","type":"education","lineage":["https://openalex.org/I135310074"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ruixuan Tu","raw_affiliation_strings":["University of Wisconsin-Madison"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Wisconsin-Madison","institution_ids":["https://openalex.org/I135310074"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5008923050","display_name":"Forrest Sheng Bao","orcid":"https://orcid.org/0000-0002-5722-5337","observed_orcids":["https://orcid.org/0000-0002-5722-5337"]},"institutions":[{"id":"https://openalex.org/I135310074","display_name":"University of Wisconsin\u2013Madison","ror":"https://ror.org/01y2jtd41","country_code":"US","type":"education","lineage":["https://openalex.org/I135310074"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Forrest Sheng Bao","raw_affiliation_strings":["University of Wisconsin-Madison"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Wisconsin-Madison","institution_ids":["https://openalex.org/I135310074"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":35.8255,"has_fulltext":true,"cited_by_count":51,"citation_normalized_percentile":{"value":0.99870668,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":99,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"2155","last_page":"2177"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.8690999746322632,"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":0.8690999746322632,"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/T10286","display_name":"Information Retrieval and Search Behavior","score":0.12559999525547028,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.0010999999940395355,"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/semantic-chunking","display_name":"semantic chunking","score":1.0},{"id":"https://openalex.org/keywords/retrieval-augmented-generation","display_name":"retrieval-augmented generation","score":0.9909999966621399},{"id":"https://openalex.org/keywords/document-chunking","display_name":"document chunking","score":0.6859999895095825},{"id":"https://openalex.org/keywords/evidence-retrieval","display_name":"evidence retrieval","score":0.7409999966621399},{"id":"https://openalex.org/keywords/document-retrieval","display_name":"document retrieval","score":0.7879999876022339},{"id":"https://openalex.org/keywords/computational-cost","display_name":"computational cost","score":0.8920000195503235},{"id":"https://openalex.org/keywords/chunking-strategies","display_name":"chunking strategies","score":0.5740000009536743}],"concepts":[{"id":"https://openalex.org/C203357204","wikidata":"https://www.wikidata.org/wiki/Q1089605","display_name":"Chunking (psychology)","level":2,"score":0.8765202760696411},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7086244821548462},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4940100312232971},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4531252384185791}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.18653/v1/2025.findings-naacl.114","doi":"https://doi.org/10.18653/v1/2025.findings-naacl.114","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.findings-naacl.114","pdf_url":"https://aclanthology.org/2025.findings-naacl.114.pdf","source":{"id":"https://openalex.org/S4363605604","display_name":"Findings of the Association for Computational Linguistics: NAACL","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":"Findings of the Association for Computational Linguistics: NAACL 2025","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2410.13070","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2410.13070","pdf_url":"https://arxiv.org/pdf/2410.13070","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,"listed_in":[],"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-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2410.13070","doi":"https://doi.org/10.48550/arxiv.2410.13070","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2410.13070","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,"listed_in":[],"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":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"doi:10.18653/v1/2025.findings-naacl.114","doi":"https://doi.org/10.18653/v1/2025.findings-naacl.114","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.findings-naacl.114","pdf_url":"https://aclanthology.org/2025.findings-naacl.114.pdf","source":{"id":"https://openalex.org/S4363605604","display_name":"Findings of the Association for Computational Linguistics: NAACL","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":"Findings of the Association for Computational Linguistics: NAACL 2025","raw_type":"proceedings-article"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4411113004.pdf","grobid_xml":"https://content.openalex.org/works/W4411113004.grobid-xml"},"referenced_works_count":7,"referenced_works":["https://openalex.org/W2986670164","https://openalex.org/W3016913119","https://openalex.org/W3165895465","https://openalex.org/W4390962494","https://openalex.org/W4402670856","https://openalex.org/W4403753183","https://openalex.org/W4404783040"],"related_works":["https://openalex.org/W7125362215","https://openalex.org/W7162291267","https://openalex.org/W4416936462","https://openalex.org/W7154900482","https://openalex.org/W7167231154","https://openalex.org/W7163175825","https://openalex.org/W7125352456","https://openalex.org/W7162122905","https://openalex.org/W7130376121","https://openalex.org/W7152125419"],"abstract_inverted_index":{"Recent":[0],"advances":[1],"in":[2,99],"Retrieval-Augmented":[3],"Generation":[4],"(RAG)":[5],"systems":[6],"have":[7],"popularized":[8],"semantic":[9,50,73,88],"chunking,":[10,33],"which":[11],"aims":[12],"to":[13],"improve":[14],"retrieval":[15],"performance":[16,80],"by":[17,78],"dividing":[18],"documents":[19,35],"into":[20,38],"semantically":[21],"coherent":[22],"segments.Despite":[23],"its":[24],"growing":[25],"adoption,":[26],"the":[27,47,68,84,92],"actual":[28],"benefits":[29],"over":[30],"simpler":[31],"fixed-size":[32,40],"where":[34],"are":[36,75],"split":[37],"consecutive,":[39],"segments,":[41],"remain":[42],"unclear.This":[43],"study":[44],"systematically":[45],"evaluates":[46],"effectiveness":[48],"of":[49],"chunking":[51,74,89,97],"using":[52],"three":[53],"common":[54],"retrieval-related":[55],"tasks:":[56],"document":[57],"retrieval,":[58,60],"evidence":[59],"and":[61,90],"retrievalbased":[62],"answer":[63],"generation.The":[64],"results":[65],"show":[66],"that":[67],"computational":[69],"costs":[70],"associated":[71],"with":[72],"not":[76],"justified":[77],"consistent":[79],"gains.These":[81],"findings":[82],"challenge":[83],"previous":[85],"assumptions":[86],"about":[87],"highlight":[91],"need":[93],"for":[94],"more":[95],"efficient":[96],"strategies":[98],"RAG":[100],"systems.":[101]},"counts_by_year":[{"year":2026,"cited_by_count":36},{"year":2025,"cited_by_count":15}],"updated_date":"2026-11-04T10:54:05.112534","created_date":"2025-10-10T00:00:00"}