{"id":"https://openalex.org/W4416034634","doi":"https://doi.org/10.18653/v1/2025.findings-emnlp.522","title":"Efficient Dynamic Clustering-Based Document Compression for Retrieval-Augmented-Generation","display_name":"Efficient Dynamic Clustering-Based Document Compression for Retrieval-Augmented-Generation","publication_year":2025,"publication_date":"2025-01-01","ids":{"openalex":"https://openalex.org/W4416034634","doi":"https://doi.org/10.18653/v1/2025.findings-emnlp.522"},"language":null,"primary_location":{"id":"doi:10.18653/v1/2025.findings-emnlp.522","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.findings-emnlp.522","pdf_url":"https://aclanthology.org/2025.findings-emnlp.522.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: EMNLP 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-emnlp.522.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5100646156","display_name":"Weitao Li","orcid":"https://orcid.org/0000-0001-6663-4864"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Weitao Li","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5115028456","display_name":"Xiangyu Zhang","orcid":"https://orcid.org/0009-0000-6271-746X"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xiangyu Zhang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103240807","display_name":"Kaiming Liu","orcid":"https://orcid.org/0000-0001-9264-6631"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Kaiming Liu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102586784","display_name":"Xuanyu Lei","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xuanyu Lei","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101524043","display_name":"Weizhi Ma","orcid":"https://orcid.org/0000-0001-5604-7527"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Weizhi Ma","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5100356161","display_name":"Yang Liu","orcid":"https://orcid.org/0000-0003-3800-3533"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yang Liu","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":2,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"9833","last_page":"9849"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11269","display_name":"Algorithms and Data Compression","score":0.47780001163482666,"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/T11269","display_name":"Algorithms and Data Compression","score":0.47780001163482666,"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":0.14659999310970306,"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/T10901","display_name":"Advanced Data Compression Techniques","score":0.07249999791383743,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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/compression","display_name":"Compression (physics)","score":0.49459999799728394},{"id":"https://openalex.org/keywords/data-compression","display_name":"Data compression","score":0.45260000228881836},{"id":"https://openalex.org/keywords/image-compression","display_name":"Image compression","score":0.25270000100135803},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.24570000171661377}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6154999732971191},{"id":"https://openalex.org/C180016635","wikidata":"https://www.wikidata.org/wiki/Q2712821","display_name":"Compression (physics)","level":2,"score":0.49459999799728394},{"id":"https://openalex.org/C78548338","wikidata":"https://www.wikidata.org/wiki/Q2493","display_name":"Data compression","level":2,"score":0.45260000228881836},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3544999957084656},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.3246999979019165},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.26179999113082886},{"id":"https://openalex.org/C13481523","wikidata":"https://www.wikidata.org/wiki/Q412438","display_name":"Image compression","level":4,"score":0.25270000100135803},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.24619999527931213},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.24570000171661377},{"id":"https://openalex.org/C9652623","wikidata":"https://www.wikidata.org/wiki/Q190109","display_name":"Field (mathematics)","level":2,"score":0.22830000519752502}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.18653/v1/2025.findings-emnlp.522","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.findings-emnlp.522","pdf_url":"https://aclanthology.org/2025.findings-emnlp.522.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: EMNLP 2025","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.18653/v1/2025.findings-emnlp.522","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.findings-emnlp.522","pdf_url":"https://aclanthology.org/2025.findings-emnlp.522.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: EMNLP 2025","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G1111291411","display_name":null,"funder_award_id":"62276152","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/F4320334978","display_name":"Beijing Nova Program","ror":"https://ror.org/034k14f91"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4416034634.pdf","grobid_xml":"https://content.openalex.org/works/W4416034634.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Retrieval-Augmented":[0],"Generation":[1],"(RAG)":[2],"has":[3],"emerged":[4],"as":[5],"a":[6],"widely":[7,91],"adopted":[8],"approach":[9],"for":[10],"knowledge":[11],"injection":[12],"during":[13],"large":[14],"language":[15],"model":[16],"(LLM)":[17],"inference":[18],"in":[19,37,50],"recent":[20],"years.However,":[21],"due":[22],"to":[23,27],"their":[24],"limited":[25],"ability":[26],"exploit":[28],"fine-grained":[29],"inter-document":[30,72],"relationships,":[31],"current":[32],"RAG":[33],"implementations":[34],"face":[35],"challenges":[36],"effectively":[38],"addressing":[39],"the":[40,51],"retrieved":[41],"noise":[42],"and":[43,79,88,94,109,115],"redundancy":[44],"content,":[45],"which":[46],"may":[47],"cause":[48],"error":[49],"generation":[52],"results.To":[53],"address":[54],"these":[55],"limitations,":[56],"we":[57],"propose":[58],"an":[59],"Efficient":[60],"Dynamic":[61],"Clustering-based":[62],"document":[63],"Compression":[64],"framework":[65],"(EDC":[66],"2":[67],"-RAG)":[68],"that":[69,99],"utilizes":[70],"latent":[71],"relationships":[73],"while":[74],"simultaneously":[75],"removing":[76],"irrelevant":[77],"information":[78],"redundant":[80],"content.We":[81],"validate":[82],"our":[83,100],"approach,":[84],"built":[85],"upon":[86],"GPT-3.5-Turbo":[87],"GPT-4o-mini,":[89],"on":[90],"used":[92],"knowledge-QA":[93],"Hallucination-Detection":[95],"datasets.Experimental":[96],"results":[97],"show":[98],"method":[101],"achieves":[102],"consistent":[103],"performance":[104],"improvements":[105],"across":[106],"various":[107],"scenarios":[108],"experimental":[110],"settings,":[111],"demonstrating":[112],"strong":[113],"robustness":[114],"applicability.":[116]},"counts_by_year":[{"year":2026,"cited_by_count":2}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-11-08T00:00:00"}