{"id":"https://openalex.org/W4412888941","doi":"https://doi.org/10.18653/v1/2025.findings-acl.20","title":"TreeRAG: Unleashing the Power of Hierarchical Storage for Enhanced Knowledge Retrieval in Long Documents","display_name":"TreeRAG: Unleashing the Power of Hierarchical Storage for Enhanced Knowledge Retrieval in Long Documents","publication_year":2025,"publication_date":"2025-01-01","ids":{"openalex":"https://openalex.org/W4412888941","doi":"https://doi.org/10.18653/v1/2025.findings-acl.20"},"language":"en","primary_location":{"id":"doi:10.18653/v1/2025.findings-acl.20","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.findings-acl.20","pdf_url":"https://aclanthology.org/2025.findings-acl.20.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.20.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5045493327","display_name":"Wenyu Tao","orcid":"https://orcid.org/0000-0002-6180-3072"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wenyu Tao","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5036301580","display_name":"Xiaofen Xing","orcid":"https://orcid.org/0000-0002-0016-9055"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xiaofen Xing","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101534540","display_name":"Yirong Chen","orcid":"https://orcid.org/0000-0002-0207-0067"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yirong Chen","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5028482510","display_name":"Linyi Huang","orcid":"https://orcid.org/0000-0003-3614-0286"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Linyi Huang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5103650199","display_name":"Xiangmin Xu","orcid":"https://orcid.org/0000-0002-8652-1194"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xiangmin Xu","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":3,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"356","last_page":"371"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.8328999876976013,"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":0.8328999876976013,"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":0.7222694158554077},{"id":"https://openalex.org/keywords/power","display_name":"Power (physics)","score":0.4939349293708801},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.48464590311050415},{"id":"https://openalex.org/keywords/information-storage","display_name":"Information storage","score":0.4315507411956787}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7222694158554077},{"id":"https://openalex.org/C163258240","wikidata":"https://www.wikidata.org/wiki/Q25342","display_name":"Power (physics)","level":2,"score":0.4939349293708801},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.48464590311050415},{"id":"https://openalex.org/C2988424471","wikidata":"https://www.wikidata.org/wiki/Q193395","display_name":"Information storage","level":2,"score":0.4315507411956787},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.18653/v1/2025.findings-acl.20","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.findings-acl.20","pdf_url":"https://aclanthology.org/2025.findings-acl.20.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.20","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.findings-acl.20","pdf_url":"https://aclanthology.org/2025.findings-acl.20.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":[],"funders":[{"id":"https://openalex.org/F4320337111","display_name":"Basic and Applied Basic Research Foundation of Guangdong Province","ror":null}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4412888941.pdf","grobid_xml":"https://content.openalex.org/works/W4412888941.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/W4396696052"],"abstract_inverted_index":{"When":[0],"confronting":[1],"long":[2,133],"document":[3,134],"information":[4],"retrieval":[5],"for":[6,49],"Query-Focused":[7],"Summarization(QFS),":[8],"Traditional":[9],"Retrieval-Augmented":[10],"Generation(RAG)":[11],"frameworks":[12,27],"struggle":[13],"to":[14,82,114,124],"retrieve":[15,23,63,83],"all":[16],"relevant":[17],"chunks,":[18],"and":[19,22,34,51,61,77,94,111,116,120],"the":[20,30,35,38,72,80,91,98],"chunking":[21,50],"strategies":[24],"of":[25,37,97],"existing":[26,118],"may":[28],"disrupt":[29],"connections":[31],"between":[32],"chunks":[33,76],"integrity":[36],"information.To":[39],"address":[40],"these":[41],"issues,":[42],"we":[43],"propose":[44],"TreeRAG,":[45],"which":[46],"employs":[47],"Tree-Chunking":[48],"embedding":[52],"in":[53,107,132],"a":[54,129],"tree-like":[55],"structure":[56,74],",":[57],"coupled":[58],"with":[59],"\"rootto-leaves\"":[60],"\"leaf-to-roots\"":[62],"strategy":[64],"named":[65],"Bidirectional":[66],"Traversal":[67],"Retrieval.This":[68],"approach":[69],"effectively":[70],"preserves":[71],"hierarchical":[73],"among":[75],"significantly":[78],"enhances":[79],"ability":[81],"while":[84],"minimizing":[85],"noise":[86],"inference.Our":[87],"experimental":[88],"results":[89],"on":[90],"Finance,":[92],"Law,":[93],"Medical":[95],"subsets":[96],"Dragonball":[99],"dataset":[100],"demonstrate":[101],"that":[102],"TreeRAG":[103],"achieves":[104,121],"significant":[105],"enhancements":[106],"both":[108],"recall":[109],"quality":[110],"precision":[112],"compared":[113],"traditional":[115],"popular":[117],"methods":[119],"better":[122],"performance":[123],"corresponding":[125],"question-answering":[126],"tasks,":[127],"marking":[128],"new":[130],"breakthrough":[131],"knowledge":[135],"retrieval.":[136]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":1}],"updated_date":"2026-07-21T08:15:58.654021","created_date":"2025-10-10T00:00:00"}