{"id":"https://openalex.org/W4416034027","doi":"https://doi.org/10.18653/v1/2025.findings-emnlp.1283","title":"D2CS - Documents Graph Clustering using LLM supervision","display_name":"D2CS - Documents Graph Clustering using LLM supervision","publication_year":2025,"publication_date":"2025-01-01","ids":{"openalex":"https://openalex.org/W4416034027","doi":"https://doi.org/10.18653/v1/2025.findings-emnlp.1283"},"language":null,"primary_location":{"id":"doi:10.18653/v1/2025.findings-emnlp.1283","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.findings-emnlp.1283","pdf_url":"https://aclanthology.org/2025.findings-emnlp.1283.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":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://aclanthology.org/2025.findings-emnlp.1283.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Yoel Ashkenazi","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yoel Ashkenazi","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5104176101","display_name":"Etzion Harari","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Etzion Harari","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5120308474","display_name":"Regev Yehezkel Imra","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Regev Yehezkel Imra","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102561753","display_name":"Naphtali Abudarham","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Naphtali Abudarham","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":null,"display_name":"Dekel Cohen","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Dekel Cohen","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5083239943","display_name":"Yoram Louzoun","orcid":"https://orcid.org/0000-0003-1714-6148"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yoram Louzoun","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":6,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.25501453,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"23606","last_page":"23623"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11710","display_name":"Biomedical Text Mining and Ontologies","score":0.0892999991774559,"subfield":{"id":"https://openalex.org/subfields/1312","display_name":"Molecular Biology"},"field":{"id":"https://openalex.org/fields/13","display_name":"Biochemistry, Genetics and Molecular Biology"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}},"topics":[{"id":"https://openalex.org/T11710","display_name":"Biomedical Text Mining and Ontologies","score":0.0892999991774559,"subfield":{"id":"https://openalex.org/subfields/1312","display_name":"Molecular Biology"},"field":{"id":"https://openalex.org/fields/13","display_name":"Biochemistry, Genetics and Molecular Biology"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}},{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.06679999828338623,"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/T11550","display_name":"Text and Document Classification Technologies","score":0.065700002014637,"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/cluster-analysis","display_name":"Cluster analysis","score":0.4887000024318695},{"id":"https://openalex.org/keywords/graph","display_name":"Graph","score":0.45989999175071716},{"id":"https://openalex.org/keywords/field","display_name":"Field (mathematics)","score":0.3582000136375427},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.28189998865127563},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.2678999900817871}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6680999994277954},{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.4887000024318695},{"id":"https://openalex.org/C132525143","wikidata":"https://www.wikidata.org/wiki/Q141488","display_name":"Graph","level":2,"score":0.45989999175071716},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3635999858379364},{"id":"https://openalex.org/C9652623","wikidata":"https://www.wikidata.org/wiki/Q190109","display_name":"Field (mathematics)","level":2,"score":0.3582000136375427},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.335099995136261},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.3215000033378601},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.28189998865127563},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.2678999900817871},{"id":"https://openalex.org/C12713177","wikidata":"https://www.wikidata.org/wiki/Q1900281","display_name":"Perspective (graphical)","level":2,"score":0.2662999927997589},{"id":"https://openalex.org/C17212007","wikidata":"https://www.wikidata.org/wiki/Q5511111","display_name":"Fuzzy clustering","level":3,"score":0.2615000009536743}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.18653/v1/2025.findings-emnlp.1283","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.findings-emnlp.1283","pdf_url":"https://aclanthology.org/2025.findings-emnlp.1283.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.1283","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.findings-emnlp.1283","pdf_url":"https://aclanthology.org/2025.findings-emnlp.1283.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":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4416034027.pdf","grobid_xml":"https://content.openalex.org/works/W4416034027.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Knowledge":[0],"discovery":[1],"from":[2,77],"large-scale,":[3],"heterogeneous":[4],"textual":[5],"corpora":[6],"presents":[7],"a":[8,13,38,43,78,114,143,170],"significant":[9],"challenge.Document":[10],"clustering":[11,29,53],"offers":[12],"practical":[14],"solution":[15],"by":[16],"organizing":[17],"unstructured":[18],"texts":[19],"into":[20,59],"coherent":[21],"groups":[22],"based":[23,112],"on":[24,113,131,173],"content":[25],"and":[26,49,95,106,140,150],"thematic":[27,34],"similarity.However,":[28],"does":[30],"not":[31],"inherently":[32],"ensure":[33],"consistency.Here,":[35],"we":[36,73,121],"propose":[37],"novel":[39],"framework":[40],"that":[41,120,136],"constructs":[42],"similarity":[44],"graph":[45],"over":[46],"document":[47],"embeddings":[48],"applies":[50],"iterative":[51,75,138],"graph-based":[52],"algorithms":[54],"to":[55,83,91,123],"partition":[56],"the":[57,63,85,100,125,137,147,153,159,174],"corpus":[58],"initial":[60],"clusters.To":[61],"overcome":[62],"limitations":[64],"of":[65,116,128,155,162],"conventional":[66],"methods":[67],"in":[68],"producing":[69],"semantically":[70],"consistent":[71],"clusters,":[72],"incorporate":[74],"feedback":[76],"large":[79],"language":[80],"model":[81],"(LLM)":[82],"guide":[84],"refinement":[86],"process.The":[87],"LLM":[88,109],"is":[89,111,179],"used":[90],"assess":[92],"cluster":[93],"quality":[94,175],"adjust":[96],"edge":[97],"weights":[98],"within":[99],"graph,":[101],"promoting":[102],"better":[103],"intra-cluster":[104],"cohesion":[105],"inter-cluster":[107],"separation.The":[108],"guidance":[110],"set":[115],"success":[117],"Rate":[118],"metrics":[119],"developed":[122],"measure":[124],"semantic":[126],"coherence":[127],"clusters.Experimental":[129],"results":[130],"multiple":[132],"benchmark":[133],"datasets":[134],"demonstrate":[135],"process":[139],"additional":[141],"user-supplied":[142],"priori":[144],"edges":[145],"improve":[146],"summaries'":[148],"consistency":[149],"fluency,":[151],"highlighting":[152],"importance":[154],"known":[156],"connections":[157],"among":[158],"documents.The":[160],"removal":[161],"very":[163,166],"rare":[164],"or":[165],"frequent":[167],"sentences":[168],"has":[169],"mixed":[171],"effect":[172],"scores.Our":[176],"full":[177],"code":[178],"available":[180],"here:":[181]},"counts_by_year":[],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-11-08T00:00:00"}