{"id":"https://openalex.org/W7166818174","doi":"https://doi.org/10.18653/v1/2026.findings-acl.1037","title":"UniGeM: Unifying Data Selection and Mixing via Geometric Exploration and Mining","display_name":"UniGeM: Unifying Data Selection and Mixing via Geometric Exploration and Mining","publication_year":2026,"publication_date":"2026-01-01","ids":{"openalex":"https://openalex.org/W7166818174","doi":"https://doi.org/10.18653/v1/2026.findings-acl.1037"},"language":null,"primary_location":{"id":"doi:10.18653/v1/2026.findings-acl.1037","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.findings-acl.1037","pdf_url":"https://aclanthology.org/2026.findings-acl.1037.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 2026","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://aclanthology.org/2026.findings-acl.1037.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5139788604","display_name":"Changhao Wang","orcid":null},"institutions":[{"id":"https://openalex.org/I4210090209","display_name":"Institute of Microelectronics","ror":"https://ror.org/009rw8n36","country_code":"SG","type":"facility","lineage":["https://openalex.org/I115228651","https://openalex.org/I4210090209","https://openalex.org/I91275662"]},{"id":"https://openalex.org/I4210119392","display_name":"Institute of Microelectronics","ror":"https://ror.org/02s6gs133","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210119392"]}],"countries":["CN","SG"],"is_corresponding":false,"raw_author_name":"Changhao Wang","raw_affiliation_strings":["Institute of Microelectronics of the CAS"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute of Microelectronics of the CAS","institution_ids":["https://openalex.org/I4210090209","https://openalex.org/I4210119392"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5139795071","display_name":"Yunfeiyu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yunfeiyu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5108323199","display_name":"Xinhao Yao","orcid":null},"institutions":[{"id":"https://openalex.org/I78988378","display_name":"Renmin University of China","ror":"https://ror.org/041pakw92","country_code":"CN","type":"education","lineage":["https://openalex.org/I78988378"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xinhao Yao","raw_affiliation_strings":["Renmin University of China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Renmin University of China","institution_ids":["https://openalex.org/I78988378"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5139752713","display_name":"Jiaolong Yang","orcid":null},"institutions":[{"id":"https://openalex.org/I4210090209","display_name":"Institute of Microelectronics","ror":"https://ror.org/009rw8n36","country_code":"SG","type":"facility","lineage":["https://openalex.org/I115228651","https://openalex.org/I4210090209","https://openalex.org/I91275662"]},{"id":"https://openalex.org/I4210119392","display_name":"Institute of Microelectronics","ror":"https://ror.org/02s6gs133","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210119392"]}],"countries":["CN","SG"],"is_corresponding":false,"raw_author_name":"Jiaolong Yang","raw_affiliation_strings":["Institute of Microelectronics of the CAS"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute of Microelectronics of the CAS","institution_ids":["https://openalex.org/I4210090209","https://openalex.org/I4210119392"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5139785394","display_name":"Lu Yu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Lu Yu","raw_affiliation_strings":["Ant Group"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Ant Group","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5139732246","display_name":"Junpeng Fang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Junpeng Fang","raw_affiliation_strings":["Ant Group"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Ant Group","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5139836175","display_name":"Chaobo Li","orcid":null},"institutions":[{"id":"https://openalex.org/I177477856","display_name":"Politecnico di Torino","ror":"https://ror.org/00bgk9508","country_code":"IT","type":"education","lineage":["https://openalex.org/I177477856"]},{"id":"https://openalex.org/I4210090209","display_name":"Institute of Microelectronics","ror":"https://ror.org/009rw8n36","country_code":"SG","type":"facility","lineage":["https://openalex.org/I115228651","https://openalex.org/I4210090209","https://openalex.org/I91275662"]},{"id":"https://openalex.org/I4210119392","display_name":"Institute of Microelectronics","ror":"https://ror.org/02s6gs133","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210119392"]}],"countries":["CN","IT","SG"],"is_corresponding":false,"raw_author_name":"Chaobo Li","raw_affiliation_strings":["Institute of Microelectronics of the CAS","University of Chinese Academy of Sciences , and Politecnico di Torino "],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute of Microelectronics of the CAS","institution_ids":["https://openalex.org/I4210090209","https://openalex.org/I4210119392"]},{"raw_affiliation_string":"University of Chinese Academy of Sciences , and Politecnico di Torino ","institution_ids":["https://openalex.org/I177477856"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5089672314","display_name":"Riccardo Cantoro","orcid":"https://orcid.org/0000-0002-1745-5293"},"institutions":[{"id":"https://openalex.org/I177477856","display_name":"Politecnico di Torino","ror":"https://ror.org/00bgk9508","country_code":"IT","type":"education","lineage":["https://openalex.org/I177477856"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Riccardo Cantoro","raw_affiliation_strings":["Politecnico di Torino"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Politecnico di Torino","institution_ids":["https://openalex.org/I177477856"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5139781887","display_name":"Qing Cui","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Qing Cui","raw_affiliation_strings":["Ant Group"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Ant Group","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5139850985","display_name":"Jun Zhou","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jun Zhou","raw_affiliation_strings":["Ant Group"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Ant Group","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":4,"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":0.83745236,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"20696","last_page":"20714"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12292","display_name":"Graph Theory and Algorithms","score":0.16529999673366547,"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"}},"topics":[{"id":"https://openalex.org/T12292","display_name":"Graph Theory and Algorithms","score":0.16529999673366547,"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"}},{"id":"https://openalex.org/T11106","display_name":"Data Management and Algorithms","score":0.14910000562667847,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"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/T10637","display_name":"Advanced Clustering Algorithms Research","score":0.033799998462200165,"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/mixing","display_name":"Mixing (physics)","score":0.6349999904632568},{"id":"https://openalex.org/keywords/selection","display_name":"Selection (genetic algorithm)","score":0.4706000089645386},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.3000999987125397},{"id":"https://openalex.org/keywords/feature-selection","display_name":"Feature selection","score":0.28540000319480896}],"concepts":[{"id":"https://openalex.org/C138777275","wikidata":"https://www.wikidata.org/wiki/Q6884054","display_name":"Mixing (physics)","level":2,"score":0.6349999904632568},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.4966999888420105},{"id":"https://openalex.org/C81917197","wikidata":"https://www.wikidata.org/wiki/Q628760","display_name":"Selection (genetic algorithm)","level":2,"score":0.4706000089645386},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.35120001435279846},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.3361999988555908},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.3000999987125397},{"id":"https://openalex.org/C148483581","wikidata":"https://www.wikidata.org/wiki/Q446488","display_name":"Feature selection","level":2,"score":0.28540000319480896},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.2851000130176544},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.27959999442100525},{"id":"https://openalex.org/C2780977526","wikidata":"https://www.wikidata.org/wiki/Q42417149","display_name":"Data exploration","level":3,"score":0.25920000672340393}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.18653/v1/2026.findings-acl.1037","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.findings-acl.1037","pdf_url":"https://aclanthology.org/2026.findings-acl.1037.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 2026","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.18653/v1/2026.findings-acl.1037","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.findings-acl.1037","pdf_url":"https://aclanthology.org/2026.findings-acl.1037.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 2026","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7166818174.pdf","grobid_xml":"https://content.openalex.org/works/W7166818174.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"The":[0],"scaling":[1],"of":[2],"Large":[3],"Language":[4],"Models":[5],"(LLMs)":[6],"is":[7],"increasingly":[8],"limited":[9],"by":[10,38,70,78],"data":[11,15,40,91],"quality.Most":[12],"methods":[13,105],"handle":[14],"mixing":[16,35,61],"and":[17,36,81,97,109],"sample":[18],"selection":[19,37],"separately,":[20],"which":[21],"can":[22],"break":[23],"the":[24],"structure":[25],"in":[26,106],"code":[27],"corpora.We":[28],"introduce":[29],"UniGeM,":[30],"a":[31,43,94],"framework":[32],"that":[33],"unifies":[34],"treating":[39],"curation":[41],"as":[42],"manifold":[44],"approximation":[45],"problem":[46],"without":[47],"training":[48,79],"proxy":[49],"models":[50,84],"or":[51],"relying":[52],"on":[53,85],"external":[54],"reference":[55],"datasets.UniGeM":[56],"operates":[57],"hierarchically:":[58],"Macro-Exploration":[59],"learns":[60],"weights":[62],"with":[63],"stability-based":[64],"clustering;":[65],"Micro-Mining":[66],"filters":[67],"high-quality":[68],"instances":[69],"their":[71],"geometric":[72],"distribution":[73],"to":[74,103],"ensure":[75],"logical":[76],"consistency.Validated":[77],"8B":[80],"16B":[82],"MoE":[83],"100B":[86],"tokens,":[87],"UniGeM":[88],"achieves":[89],"2.0\u00d7":[90],"efficiency":[92],"over":[93],"random":[95],"baseline":[96],"further":[98],"improves":[99],"overall":[100],"performance":[101],"compared":[102],"SOTA":[104],"reasoning-heavy":[107],"evaluations":[108],"multilingual":[110],"generalization.":[111]},"counts_by_year":[],"updated_date":"2026-08-21T09:56:20.448147","created_date":"2026-07-02T00:00:00"}