{"id":"https://openalex.org/W7204178369","doi":"https://doi.org/10.5281/zenodo.22101314","title":"LLMs as the Clustering Algorithm: A Cost-Quality-Interpretability Analysis of LLM-Direct Text Clustering","display_name":"LLMs as the Clustering Algorithm: A Cost-Quality-Interpretability Analysis of LLM-Direct Text Clustering","publication_year":2026,"publication_date":"2026-08-25","ids":{"openalex":"https://openalex.org/W7204178369","doi":"https://doi.org/10.5281/zenodo.22101314"},"language":"en","primary_location":{"id":"doi:10.5281/zenodo.22101314","doi":"https://doi.org/10.5281/zenodo.22101314","is_oa":true,"landing_page_url":"https://doi.org/10.5281/zenodo.22101314","pdf_url":null,"source":{"id":"https://openalex.org/S4306400562","display_name":"Zenodo (CERN European Organization for Nuclear Research)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I67311998","host_organization_name":"European Organization for Nuclear Research","host_organization_lineage":["https://openalex.org/I67311998"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"},"volume":null,"type":"preprint","indexed_in":["datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://doi.org/10.5281/zenodo.22101314","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5148174329","display_name":"Sirui Ray Li","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Li, Sirui Ray","raw_affiliation_strings":["Independent Researcher"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Independent Researcher","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":["https://openalex.org/A5148174329"],"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":false,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.6538000106811523,"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":0.6538000106811523,"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/T10637","display_name":"Advanced Clustering Algorithms Research","score":0.23749999701976776,"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/T13910","display_name":"Computational and Text Analysis Methods","score":0.09290000051259995,"subfield":{"id":"https://openalex.org/subfields/3300","display_name":"General Social Sciences"},"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/interpretability","display_name":"interpretability","score":0.597000002861023},{"id":"https://openalex.org/keywords/incremental-strategy","display_name":"incremental strategy","score":0.9070000052452087}],"concepts":[{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.7767999768257141},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5918999910354614},{"id":"https://openalex.org/C2781067378","wikidata":"https://www.wikidata.org/wiki/Q17027399","display_name":"Interpretability","level":2,"score":0.5723999738693237},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.491100013256073},{"id":"https://openalex.org/C177937566","wikidata":"https://www.wikidata.org/wiki/Q4223102","display_name":"Document clustering","level":3,"score":0.4745999872684479},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.47450000047683716},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.4268999993801117},{"id":"https://openalex.org/C184898388","wikidata":"https://www.wikidata.org/wiki/Q1435712","display_name":"Pairwise comparison","level":2,"score":0.4049000144004822},{"id":"https://openalex.org/C61224824","wikidata":"https://www.wikidata.org/wiki/Q2260434","display_name":"Mixture model","level":2,"score":0.35830000042915344},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.34369999170303345},{"id":"https://openalex.org/C58041806","wikidata":"https://www.wikidata.org/wiki/Q1660484","display_name":"Imputation (statistics)","level":3,"score":0.32600000500679016},{"id":"https://openalex.org/C2778755073","wikidata":"https://www.wikidata.org/wiki/Q10858537","display_name":"Scale (ratio)","level":2,"score":0.30309998989105225},{"id":"https://openalex.org/C168065819","wikidata":"https://www.wikidata.org/wiki/Q845566","display_name":"Debugging","level":2,"score":0.29919999837875366},{"id":"https://openalex.org/C199845137","wikidata":"https://www.wikidata.org/wiki/Q145490","display_name":"Network topology","level":2,"score":0.2944999933242798},{"id":"https://openalex.org/C17212007","wikidata":"https://www.wikidata.org/wiki/Q5511111","display_name":"Fuzzy clustering","level":3,"score":0.2937000095844269},{"id":"https://openalex.org/C92835128","wikidata":"https://www.wikidata.org/wiki/Q1277447","display_name":"Hierarchical clustering","level":3,"score":0.2842999994754791},{"id":"https://openalex.org/C43521106","wikidata":"https://www.wikidata.org/wiki/Q2165493","display_name":"Pipeline (software)","level":2,"score":0.2754000127315521},{"id":"https://openalex.org/C94641424","wikidata":"https://www.wikidata.org/wiki/Q5172845","display_name":"Correlation clustering","level":3,"score":0.27300000190734863},{"id":"https://openalex.org/C177774035","wikidata":"https://www.wikidata.org/wiki/Q1246948","display_name":"Granularity","level":2,"score":0.2678999900817871},{"id":"https://openalex.org/C55166926","wikidata":"https://www.wikidata.org/wiki/Q2892946","display_name":"Oracle","level":2,"score":0.26739999651908875},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.259799987077713},{"id":"https://openalex.org/C36382193","wikidata":"https://www.wikidata.org/wiki/Q7068966","display_name":"Null model","level":2,"score":0.2556000053882599},{"id":"https://openalex.org/C167984511","wikidata":"https://www.wikidata.org/wiki/Q17003931","display_name":"Brown clustering","level":5,"score":0.25440001487731934},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.2533000111579895},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.2502000033855438},{"id":"https://openalex.org/C2777601683","wikidata":"https://www.wikidata.org/wiki/Q6499736","display_name":"Vocabulary","level":2,"score":0.2500999867916107}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.5281/zenodo.22101314","doi":"https://doi.org/10.5281/zenodo.22101314","is_oa":true,"landing_page_url":"https://doi.org/10.5281/zenodo.22101314","pdf_url":null,"source":{"id":"https://openalex.org/S4306400562","display_name":"Zenodo (CERN European Organization for Nuclear Research)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I67311998","host_organization_name":"European Organization for Nuclear Research","host_organization_lineage":["https://openalex.org/I67311998"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"Preprint"},{"id":"doi:10.5281/zenodo.22101315","doi":"https://doi.org/10.5281/zenodo.22101315","is_oa":true,"landing_page_url":"https://doi.org/10.5281/zenodo.22101315","pdf_url":null,"source":{"id":"https://openalex.org/S4306400562","display_name":"Zenodo (CERN European Organization for Nuclear Research)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I67311998","host_organization_name":"European Organization for Nuclear Research","host_organization_lineage":["https://openalex.org/I67311998"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"doi:10.5281/zenodo.22101314","doi":"https://doi.org/10.5281/zenodo.22101314","is_oa":true,"landing_page_url":"https://doi.org/10.5281/zenodo.22101314","pdf_url":null,"source":{"id":"https://openalex.org/S4306400562","display_name":"Zenodo (CERN European Organization for Nuclear Research)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I67311998","host_organization_name":"European Organization for Nuclear Research","host_organization_lineage":["https://openalex.org/I67311998"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"},"sustainable_development_goals":[],"sustainable_development_goals_aurora":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"The":[0,187],"standard":[1],"pipeline":[2],"for":[3],"text":[4],"clustering":[5,11,43,188],"(embed,":[6],"then":[7,99],"run":[8],"a":[9,20,35,47,75,88,95,166,183,236,258],"geometric":[10],"algorithm)":[12],"produces":[13],"clusters":[14],"that":[15,33],"are":[16],"accurate":[17],"but":[18],"opaque:":[19],"practitioner":[21],"debugging":[22],"the":[23,41,51,104,136,147,169,176,200,244,249],"output":[24,121],"sees":[25],"anonymous":[26],"centroids,":[27],"not":[28,154],"reasons.":[29],"We":[30,107,264],"study":[31],"methods":[32],"use":[34],"large":[36],"language":[37],"model":[38,230],"(LLM)":[39],"as":[40,182],"entire":[42],"operator,":[44],"and":[45,79,113,123,232],"provide":[46],"controlled":[48],"comparison":[49],"of":[50,198,240],"natural":[52],"inference":[53],"topologies":[54],"under":[55],"one":[56,67,82],"oracle":[57],"abstraction:":[58],"three":[59],"base":[60],"strategies,":[61],"FullContext":[62,213],"(the":[63],"whole":[64],"corpus":[65,241],"in":[66],"call),":[68,78],"ChunkMerge":[69],"(parallel":[70],"chunk":[71],"clusterings":[72],"unified":[73],"by":[74,195,235],"prototype":[76],"merge":[77],"Incremental":[80],"(online,":[81],"assign-or-create":[83],"call":[84,93],"per":[85,163,222],"item),":[86],"plus":[87],"derived":[89],"hybrid,":[90],"SampleSeed":[91],"(one":[92],"over":[94],"random":[96],"seed":[97],"sample,":[98],"parallel":[100],"batch":[101],"assignment":[102],"against":[103,126],"frozen":[105],"result).":[106],"derive":[108],"each":[109,267],"strategy's":[110],"cost":[111,250],"profile":[112],"measure":[114],"quality,":[115],"dollar":[116],"cost,":[117],"latency,":[118],"order":[119],"sensitivity,":[120],"reliability,":[122],"label":[124],"interpretability":[125],"embedding":[127,149],"baselines":[128],"on":[129,156,165,172],"four":[130],"corpora.":[131],"On":[132],"noisy":[133],"financial":[134],"tweets":[135],"best":[137],"cost-tier":[138],"LLM":[139,201],"configurations":[140],"obtain":[141],"mean":[142],"ARI":[143,203,253],"numerically":[144],"comparable":[145],"to":[146,193],"strongest":[148],"baseline":[150],"(0.25-0.29":[151],"vs.":[152],"0.25,":[153],"significant":[155],"this":[157],"fixed":[158],"sample)":[159],"at":[160,209,224,248,255],"USD":[161],"0.02-0.65":[162],"run;":[164],"coarse":[167],"control":[168],"outcome":[170],"depends":[171],"who":[173],"is":[174,190,243],"told":[175],"true":[177],"k,":[178],"implicating":[179],"granularity":[180],"alignment":[181],"central":[184],"success":[185],"factor.":[186],"criterion":[189],"promptable:":[191],"asked":[192],"cluster":[194],"sentiment":[196],"instead":[197],"topic,":[199],"reaches":[202],"0.30":[204],"where":[205],"generic":[206],"embeddings":[207],"stay":[208],"or":[210],"below":[211],"0.08.":[212],"degrades":[214],"catastrophically":[215],"with":[216,257],"scale":[217],"(over":[218],"2":[219],"output-repair":[220],"events":[221],"item":[223],"N=1000),":[225],"strategy":[226],"rankings":[227],"change":[228],"across":[229],"tiers,":[231],"SampleSeed,":[233],"sized":[234],"coverage":[237],"bound":[238],"independent":[239],"size,":[242],"most":[245],"scale-stable":[246],"configuration":[247],"tier,":[251],"holding":[252],"0.27":[254],"N=1000":[256],"flat":[259],"10-25":[260],"second":[261],"critical":[262],"path.":[263],"quantify":[265],"what":[266],"choice":[268],"costs.":[269]},"counts_by_year":[],"updated_date":"2026-10-07T09:51:55.459714","created_date":"2026-08-26T00:00:00"}