{"id":"https://openalex.org/W4412888476","doi":"https://doi.org/10.18653/v1/2025.findings-acl.422","title":"Document Segmentation Matters for Retrieval-Augmented Generation","display_name":"Document Segmentation Matters for Retrieval-Augmented Generation","publication_year":2025,"publication_date":"2025-01-01","ids":{"openalex":"https://openalex.org/W4412888476","doi":"https://doi.org/10.18653/v1/2025.findings-acl.422"},"language":"en","primary_location":{"id":"doi:10.18653/v1/2025.findings-acl.422","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.findings-acl.422","pdf_url":"https://aclanthology.org/2025.findings-acl.422.pdf","source":null,"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: ACL 2025","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://aclanthology.org/2025.findings-acl.422.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5039766108","display_name":"Zhitong Wang","orcid":"https://orcid.org/0000-0001-9523-7163"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhitong Wang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101699465","display_name":"Cheng Gao","orcid":"https://orcid.org/0000-0002-8862-316X"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Cheng Gao","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5014699953","display_name":"Chaojun Xiao","orcid":"https://orcid.org/0000-0001-6039-0942"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Chaojun Xiao","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5068887242","display_name":"Yufei Huang","orcid":"https://orcid.org/0000-0001-6268-5357"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yufei Huang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5022397026","display_name":"Shuzheng Si","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Shuzheng Si","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5076427086","display_name":"Kangyang Luo","orcid":"https://orcid.org/0009-0002-0328-2026"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Kangyang Luo","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5113092722","display_name":"Yuzhuo Bai","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yuzhuo Bai","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100362638","display_name":"Wenhao Li","orcid":"https://orcid.org/0000-0003-2985-1098"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wenhao Li","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5015295210","display_name":"Tangjian Duan","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Tangjian Duan","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5003894157","display_name":"Chuancheng Lv","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Chuancheng Lv","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5086162908","display_name":"Guoshan Lu","orcid":"https://orcid.org/0000-0002-1732-9617"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Guoshan Lu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100389287","display_name":"Gang Chen","orcid":"https://orcid.org/0000-0002-8105-2384"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Gang Chen","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5030183493","display_name":"Fanchao Qi","orcid":"https://orcid.org/0000-0002-4400-4033"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Fanchao Qi","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5046448314","display_name":"Maosong Sun","orcid":"https://orcid.org/0000-0002-6011-6115"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Maosong Sun","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":true,"cited_by_count":10,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"8063","last_page":"8075"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10215","display_name":"Semantic Web and Ontologies","score":0.9120000004768372,"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/T10215","display_name":"Semantic Web and Ontologies","score":0.9120000004768372,"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":0.721531867980957},{"id":"https://openalex.org/keywords/segmentation","display_name":"Segmentation","score":0.5741252303123474},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.5032040476799011},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4649440348148346},{"id":"https://openalex.org/keywords/image-segmentation","display_name":"Image segmentation","score":0.45494982600212097}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.721531867980957},{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.5741252303123474},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.5032040476799011},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4649440348148346},{"id":"https://openalex.org/C124504099","wikidata":"https://www.wikidata.org/wiki/Q56933","display_name":"Image segmentation","level":3,"score":0.45494982600212097}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.18653/v1/2025.findings-acl.422","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.findings-acl.422","pdf_url":"https://aclanthology.org/2025.findings-acl.422.pdf","source":null,"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: ACL 2025","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.18653/v1/2025.findings-acl.422","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.findings-acl.422","pdf_url":"https://aclanthology.org/2025.findings-acl.422.pdf","source":null,"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: ACL 2025","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G1681167796","display_name":null,"funder_award_id":"62236011","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320322392","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549"},{"id":"https://openalex.org/F4320329860","display_name":"National Science and Technology Major Project","ror":null}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4412888476.pdf","grobid_xml":"https://content.openalex.org/works/W4412888476.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W2390279801","https://openalex.org/W4391913857","https://openalex.org/W2358668433","https://openalex.org/W4396701345","https://openalex.org/W2376932109","https://openalex.org/W2001405890","https://openalex.org/W1522196789"],"abstract_inverted_index":{"Zhitong":[0],"Wang,":[1],"Cheng":[2],"Gao,":[3],"Chaojun":[4],"Xiao,":[5],"Yufei":[6],"Huang,":[7],"Shuzheng":[8],"Si,":[9],"Kangyang":[10],"Luo,":[11],"Yuzhuo":[12],"Bai,":[13],"Wenhao":[14],"Li,":[15],"Tangjian":[16],"Duan,":[17],"Chuancheng":[18],"Lv,":[19],"Guoshan":[20],"Lu,":[21],"Gang":[22],"Chen,":[23],"Fanchao":[24],"Qi,":[25],"Maosong":[26],"Sun.":[27],"Findings":[28],"of":[29],"the":[30],"Association":[31],"for":[32],"Computational":[33],"Linguistics:":[34],"ACL":[35],"2025.":[36,37]},"counts_by_year":[{"year":2026,"cited_by_count":8},{"year":2025,"cited_by_count":2}],"updated_date":"2026-07-16T13:24:37.021932","created_date":"2025-10-10T00:00:00"}
