{"id":"https://openalex.org/W7083679346","doi":"https://doi.org/10.48550/arxiv.2509.22211","title":"LogiPart: Local Large Language Models for Data Exploration at Scale with Logical Partitioning","display_name":"LogiPart: Local Large Language Models for Data Exploration at Scale with Logical Partitioning","publication_year":2025,"publication_date":"2025-09-26","ids":{"openalex":"https://openalex.org/W7083679346","doi":"https://doi.org/10.48550/arxiv.2509.22211"},"language":"en","primary_location":{"id":"doi:10.48550/arxiv.2509.22211","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2509.22211","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"},"type":"preprint","indexed_in":["datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://doi.org/10.48550/arxiv.2509.22211","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Tavares, Tiago Fernandes","orcid":null},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Tavares, Tiago Fernandes","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":false,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":true,"primary_topic":{"id":"https://openalex.org/T13477","display_name":"Sustainable Design and Development","score":0.13199999928474426,"subfield":{"id":"https://openalex.org/subfields/2215","display_name":"Building and Construction"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T13477","display_name":"Sustainable Design and Development","score":0.13199999928474426,"subfield":{"id":"https://openalex.org/subfields/2215","display_name":"Building and Construction"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T13683","display_name":"Architecture, Art, Education","score":0.09290000051259995,"subfield":{"id":"https://openalex.org/subfields/1213","display_name":"Visual Arts and Performing Arts"},"field":{"id":"https://openalex.org/fields/12","display_name":"Arts and Humanities"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T12670","display_name":"Urbanism, Landscape, and Tourism Studies","score":0.04780000075697899,"subfield":{"id":"https://openalex.org/subfields/3316","display_name":"Cultural Studies"},"field":{"id":"https://openalex.org/fields/33","display_name":"Social Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/hierarchy","display_name":"Hierarchy","score":0.507099986076355},{"id":"https://openalex.org/keywords/thematic-map","display_name":"Thematic map","score":0.47350001335144043},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.45410001277923584},{"id":"https://openalex.org/keywords/scale","display_name":"Scale (ratio)","score":0.4383000135421753},{"id":"https://openalex.org/keywords/natural-language","display_name":"Natural language","score":0.43779999017715454},{"id":"https://openalex.org/keywords/generative-grammar","display_name":"Generative grammar","score":0.41659998893737793},{"id":"https://openalex.org/keywords/stability","display_name":"Stability (learning theory)","score":0.412200003862381},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.387800008058548},{"id":"https://openalex.org/keywords/semantics","display_name":"Semantics (computer science)","score":0.38609999418258667}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7502999901771545},{"id":"https://openalex.org/C31170391","wikidata":"https://www.wikidata.org/wiki/Q188619","display_name":"Hierarchy","level":2,"score":0.507099986076355},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.48260000348091125},{"id":"https://openalex.org/C93692415","wikidata":"https://www.wikidata.org/wiki/Q1502030","display_name":"Thematic map","level":2,"score":0.47350001335144043},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.45410001277923584},{"id":"https://openalex.org/C2778755073","wikidata":"https://www.wikidata.org/wiki/Q10858537","display_name":"Scale (ratio)","level":2,"score":0.4383000135421753},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.43779999017715454},{"id":"https://openalex.org/C39890363","wikidata":"https://www.wikidata.org/wiki/Q36108","display_name":"Generative grammar","level":2,"score":0.41659998893737793},{"id":"https://openalex.org/C112972136","wikidata":"https://www.wikidata.org/wiki/Q7595718","display_name":"Stability (learning theory)","level":2,"score":0.412200003862381},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.4065000116825104},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.39419999718666077},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.387800008058548},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.38609999418258667},{"id":"https://openalex.org/C120894424","wikidata":"https://www.wikidata.org/wiki/Q1322871","display_name":"Exploratory data analysis","level":2,"score":0.3625999987125397},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3614000082015991},{"id":"https://openalex.org/C2474386","wikidata":"https://www.wikidata.org/wiki/Q461183","display_name":"Text corpus","level":2,"score":0.34880000352859497},{"id":"https://openalex.org/C167966045","wikidata":"https://www.wikidata.org/wiki/Q5532625","display_name":"Generative model","level":3,"score":0.34459999203681946},{"id":"https://openalex.org/C2779439875","wikidata":"https://www.wikidata.org/wiki/Q1078276","display_name":"Natural language understanding","level":3,"score":0.32409998774528503},{"id":"https://openalex.org/C62611344","wikidata":"https://www.wikidata.org/wiki/Q1062658","display_name":"Node (physics)","level":2,"score":0.30399999022483826},{"id":"https://openalex.org/C48145219","wikidata":"https://www.wikidata.org/wiki/Q1335365","display_name":"Security token","level":2,"score":0.29660001397132874},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.2919999957084656},{"id":"https://openalex.org/C138268822","wikidata":"https://www.wikidata.org/wiki/Q1051925","display_name":"Resolution (logic)","level":2,"score":0.28790000081062317},{"id":"https://openalex.org/C102993220","wikidata":"https://www.wikidata.org/wiki/Q387196","display_name":"Description logic","level":2,"score":0.27000001072883606},{"id":"https://openalex.org/C155092808","wikidata":"https://www.wikidata.org/wiki/Q182557","display_name":"Computational linguistics","level":2,"score":0.257099986076355},{"id":"https://openalex.org/C120936955","wikidata":"https://www.wikidata.org/wiki/Q2155640","display_name":"Empirical research","level":2,"score":0.25360000133514404},{"id":"https://openalex.org/C146849305","wikidata":"https://www.wikidata.org/wiki/Q370766","display_name":"Ground truth","level":2,"score":0.2524999976158142},{"id":"https://openalex.org/C101468663","wikidata":"https://www.wikidata.org/wiki/Q1620158","display_name":"Modular design","level":2,"score":0.25189998745918274}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2509.22211","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2509.22211","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"doi:10.48550/arxiv.2509.22211","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2509.22211","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"The":[0],"discovery":[1,181,208],"of":[2,20,29,154,168,182],"deep,":[3],"steerable":[4],"taxonomies":[5],"in":[6],"large":[7],"text":[8,108],"corpora":[9,109,136],"is":[10],"currently":[11],"restricted":[12],"by":[13,175],"a":[14,35],"trade-off":[15],"between":[16],"the":[17,24,75,125,152,155,180],"surface-level":[18],"efficiency":[19],"topic":[21],"models":[22],"and":[23,213],"prohibitive,":[25],"non-scalable":[26],"assignment":[27],"costs":[28],"LLM-integrated":[30],"frameworks.":[31],"We":[32,102],"introduce":[33],"\\textbf{LogiPart},":[34],"scalable,":[36],"hypothesis-first":[37],"framework":[38],"for":[39,116,129],"building":[40],"interpretable":[41],"hierarchical":[42],"partitions":[43],"that":[44,190],"decouples":[45],"hierarchy":[46],"growth":[47],"from":[48],"expensive":[49],"full-corpus":[50],"LLM":[51],"conditioning.":[52],"LogiPart":[53,104,197],"utilizes":[54],"locally":[55],"hosted":[56],"LLMs":[57],"on":[58,202],"compact,":[59],"embedding-aware":[60],"samples":[61],"to":[62,99,170,195],"generate":[63],"concise":[64],"natural-language":[65],"taxonomic":[66,160,207],"predicates.":[67],"These":[68],"predicates":[69],"are":[70],"then":[71],"evaluated":[72],"efficiently":[73],"across":[74,105],"entire":[76],"corpus":[77,100],"using":[78],"zero-shot":[79],"Natural":[80],"Language":[81],"Inference":[82],"(NLI)":[83],"combined":[84],"with":[85,158],"fast":[86],"graph-based":[87],"label":[88],"propagation,":[89],"achieving":[90],"constant":[91],"$O(1)$":[92],"generative":[93],"token":[94],"complexity":[95],"per":[96],"node":[97],"relative":[98],"size.":[101],"evaluate":[103],"four":[106],"diverse":[107],"(totaling":[110],"$\\approx$140,000":[111],"documents).":[112],"Using":[113],"structured":[114],"manifolds":[115],"\\textbf{calibration},":[117],"we":[118],"identify":[119],"an":[120,145,163,176],"empirical":[121],"reasoning":[122],"threshold":[123],"at":[124],"14B-parameter":[126],"scale":[127],"required":[128],"stable":[130],"semantic":[131],"grounding.":[132],"On":[133],"complex,":[134],"high-entropy":[135],"(Wikipedia,":[137],"US":[138],"Bills),":[139],"where":[140],"traditional":[141],"thematic":[142,191],"metrics":[143],"reveal":[144],"``alignment":[146],"gap,''":[147],"inverse":[148],"logic":[149],"validation":[150],"confirms":[151,179],"stability":[153],"induced":[156],"logic,":[157],"individual":[159],"bisections":[161],"maintaining":[162],"average":[164],"per-node":[165],"routing":[166],"accuracy":[167],"up":[169],"96\\%.":[171],"A":[172],"qualitative":[173],"audit":[174],"independent":[177],"LLM-as-a-judge":[178],"meaningful":[183],"functional":[184],"axes,":[185],"such":[186],"as":[187],"policy":[188],"intent,":[189],"ground-truth":[192],"labels":[193],"fail":[194],"capture.":[196],"enables":[198],"frontier-level":[199],"exploratory":[200],"analysis":[201],"consumer-grade":[203],"hardware,":[204],"making":[205],"hypothesis-driven":[206],"feasible":[209],"under":[210],"realistic":[211],"computational":[212],"governance":[214],"constraints.":[215]},"counts_by_year":[],"updated_date":"2026-07-28T07:46:37.118299","created_date":"2025-10-10T00:00:00"}