{"id":"https://openalex.org/W7162639456","doi":"https://doi.org/10.48550/arxiv.2605.27913","title":"Where LLM Annotators Fail: Label-Free Learning on Graphs with LLMs","display_name":"Where LLM Annotators Fail: Label-Free Learning on Graphs with LLMs","publication_year":2026,"publication_date":"2026-05-27","ids":{"openalex":"https://openalex.org/W7162639456","doi":"https://doi.org/10.48550/arxiv.2605.27913"},"language":null,"primary_location":{"id":"doi:10.48550/arxiv.2605.27913","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2605.27913","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":"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"},"type":"preprint","indexed_in":["datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://doi.org/10.48550/arxiv.2605.27913","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5004087002","display_name":"Safal Thapaliya","orcid":"https://orcid.org/0000-0002-4463-6700"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Thapaliya, Safal","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5137257551","display_name":"Jiatan Huang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Huang, Jiatan","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5137222340","display_name":"Chuxu Zhang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhang, Chuxu","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":false,"primary_topic":{"id":"https://openalex.org/T11273","display_name":"Advanced Graph Neural Networks","score":0.7807999849319458,"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/T11273","display_name":"Advanced Graph Neural Networks","score":0.7807999849319458,"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/T10028","display_name":"Topic Modeling","score":0.05469999834895134,"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":0.02319999970495701,"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/ground-truth","display_name":"Ground truth","score":0.6686000227928162},{"id":"https://openalex.org/keywords/annotation","display_name":"Annotation","score":0.5961999893188477},{"id":"https://openalex.org/keywords/graph","display_name":"Graph","score":0.5824999809265137},{"id":"https://openalex.org/keywords/reliability","display_name":"Reliability (semiconductor)","score":0.489300012588501},{"id":"https://openalex.org/keywords/node","display_name":"Node (physics)","score":0.4239000082015991},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.40149998664855957},{"id":"https://openalex.org/keywords/factor-graph","display_name":"Factor graph","score":0.3230000138282776}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7229999899864197},{"id":"https://openalex.org/C146849305","wikidata":"https://www.wikidata.org/wiki/Q370766","display_name":"Ground truth","level":2,"score":0.6686000227928162},{"id":"https://openalex.org/C2776321320","wikidata":"https://www.wikidata.org/wiki/Q857525","display_name":"Annotation","level":2,"score":0.5961999893188477},{"id":"https://openalex.org/C132525143","wikidata":"https://www.wikidata.org/wiki/Q141488","display_name":"Graph","level":2,"score":0.5824999809265137},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5277000069618225},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4964999854564667},{"id":"https://openalex.org/C43214815","wikidata":"https://www.wikidata.org/wiki/Q7310987","display_name":"Reliability (semiconductor)","level":3,"score":0.489300012588501},{"id":"https://openalex.org/C62611344","wikidata":"https://www.wikidata.org/wiki/Q1062658","display_name":"Node (physics)","level":2,"score":0.4239000082015991},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.40149998664855957},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.32839998602867126},{"id":"https://openalex.org/C159246509","wikidata":"https://www.wikidata.org/wiki/Q5428725","display_name":"Factor graph","level":3,"score":0.3230000138282776},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.3190000057220459},{"id":"https://openalex.org/C2778755073","wikidata":"https://www.wikidata.org/wiki/Q10858537","display_name":"Scale (ratio)","level":2,"score":0.31679999828338623},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.3061000108718872},{"id":"https://openalex.org/C90673727","wikidata":"https://www.wikidata.org/wiki/Q901718","display_name":"Product (mathematics)","level":2,"score":0.3059000074863434},{"id":"https://openalex.org/C2129575","wikidata":"https://www.wikidata.org/wiki/Q54837","display_name":"Semantic Web","level":2,"score":0.3003000020980835},{"id":"https://openalex.org/C58041806","wikidata":"https://www.wikidata.org/wiki/Q1660484","display_name":"Imputation (statistics)","level":3,"score":0.28369998931884766},{"id":"https://openalex.org/C2776145971","wikidata":"https://www.wikidata.org/wiki/Q30673951","display_name":"Labeled data","level":2,"score":0.27790001034736633},{"id":"https://openalex.org/C96250715","wikidata":"https://www.wikidata.org/wiki/Q965330","display_name":"Estimation","level":2,"score":0.2612000107765198},{"id":"https://openalex.org/C29265498","wikidata":"https://www.wikidata.org/wiki/Q7047719","display_name":"Noise measurement","level":3,"score":0.25850000977516174}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2605.27913","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2605.27913","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":"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:10.48550/arxiv.2605.27913","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2605.27913","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":"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":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Node":[0],"classification":[1],"on":[2,147],"graphs":[3],"often":[4],"requires":[5],"labeled":[6],"nodes,":[7],"yet":[8],"obtaining":[9],"labels":[10,49,126],"at":[11],"graph":[12,55,131],"scale":[13],"is":[14],"expensive.":[15],"When":[16],"node":[17],"attributes":[18],"contain":[19],"semantic":[20],"content,":[21],"such":[22],"as":[23,62],"paper":[24],"abstracts,":[25],"web":[26],"pages,":[27],"or":[28,65],"product":[29],"descriptions,":[30],"large":[31],"language":[32],"models":[33],"(LLMs)":[34],"can":[35,85],"provide":[36],"low-cost":[37],"supervision":[38],"by":[39],"annotating":[40],"a":[41,101],"small":[42],"subset":[43],"of":[44,93],"nodes.":[45],"However,":[46],"these":[47],"LLM-generated":[48],"are":[50,73],"noisy,":[51],"and":[52,114,124,133],"existing":[53],"label-free":[54,102,141],"learning":[56,103],"methods":[57],"usually":[58],"treat":[59],"this":[60,116],"noise":[61],"either":[63],"global":[64],"class-conditional.":[66],"We":[67],"find":[68],"that":[69,105],"LLM":[70,108],"annotation":[71],"errors":[72],"not":[74],"only":[75],"class-dependent":[76],"but":[77],"also":[78],"region-dependent:":[79],"within":[80],"the":[81,139,144],"same":[82],"class,":[83],"reliability":[84,109],"vary":[86],"sharply":[87],"across":[88],"feature-space":[89],"clusters.":[90],"In":[91],"light":[92],"this,":[94],"we":[95],"propose":[96],"Cluster-Aware":[97],"Noise":[98],"Estimation":[99],"(CANE),":[100],"framework":[104],"estimates":[106],"cluster-conditional":[107,151],"without":[110],"ground":[111],"truth":[112],"labels,":[113],"uses":[115],"estimate":[117],"to":[118,122,127],"decide":[119],"which":[120,125],"pseudo-labels":[121],"trust,":[123],"correct.":[128],"Across":[129],"various":[130],"benchmarks":[132],"GNN":[134],"backbones,":[135],"CANE":[136],"improves":[137],"over":[138],"strongest":[140],"baselines,":[142],"with":[143],"largest":[145],"gains":[146],"datasets":[148],"exhibiting":[149],"stronger":[150],"noise.":[152]},"counts_by_year":[],"updated_date":"2026-07-28T07:46:37.118299","created_date":"2026-05-29T00:00:00"}