{"id":"https://openalex.org/W7140100134","doi":"https://doi.org/10.18653/v1/2026.findings-eacl.14","title":"How to Make LMs Strong Node Classifiers?","display_name":"How to Make LMs Strong Node Classifiers?","publication_year":2026,"publication_date":"2026-01-01","ids":{"openalex":"https://openalex.org/W7140100134","doi":"https://doi.org/10.18653/v1/2026.findings-eacl.14"},"language":"en","primary_location":{"id":"doi:10.18653/v1/2026.findings-eacl.14","doi":"https://doi.org/10.18653/v1/2026.findings-eacl.14","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.findings-eacl.14","pdf_url":null,"source":{"id":"https://openalex.org/S7407087051","display_name":"Findings of the Association for Computational Linguistics: EACL","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"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: EACL 2026","raw_type":"proceedings-article"},"volume":null,"type":"conference-paper","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://doi.org/10.18653/v1/2026.findings-eacl.14","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5130329996","display_name":"Zhe Xu","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhe Xu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5072012496","display_name":"Kaveh Hassani","orcid":"https://orcid.org/0000-0001-9162-9442","observed_orcids":["https://orcid.org/0000-0001-9162-9442"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Kaveh Hassani","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5130352296","display_name":"Si Zhang","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Si Zhang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5125406758","display_name":"Hanqing Zeng","orcid":"https://orcid.org/0000-0002-2578-2147","observed_orcids":["https://orcid.org/0000-0002-2578-2147"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Hanqing Zeng","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5005898634","display_name":"Michihiro Yasunaga","orcid":"https://orcid.org/0009-0003-3008-927X","observed_orcids":["https://orcid.org/0009-0003-3008-927X"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Michihiro Yasunaga","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5090907829","display_name":"Limei Wang","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Limei Wang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5028848091","display_name":"Dongqi Fu","orcid":"https://orcid.org/0000-0002-8726-9234","observed_orcids":["https://orcid.org/0000-0002-8726-9234"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Dongqi Fu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5008059630","display_name":"Ning Yao","orcid":"https://orcid.org/0009-0008-5585-5424","observed_orcids":["https://orcid.org/0009-0008-5585-5424","https://orcid.org/0009-0007-0335-1964"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ning Yao","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5130372244","display_name":"Bo Long","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Bo Long","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5068043486","display_name":"Hanghang Tong","orcid":"https://orcid.org/0000-0003-4405-3887","observed_orcids":["https://orcid.org/0000-0003-4405-3887"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Hanghang Tong","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":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.14769905,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"252","last_page":"274"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11273","display_name":"Advanced Graph Neural Networks","score":0.9761000275611877,"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":0.9761000275611877,"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":0.003599999938160181,"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/T10064","display_name":"Complex Network Analysis Techniques","score":0.002899999963119626,"subfield":{"id":"https://openalex.org/subfields/3109","display_name":"Statistical and Nonlinear Physics"},"field":{"id":"https://openalex.org/fields/31","display_name":"Physics and Astronomy"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/node-classification","display_name":"node classification","score":0.8040000200271606},{"id":"https://openalex.org/keywords/large-language-models","display_name":"large language models","score":0.7850000262260437},{"id":"https://openalex.org/keywords/graph-neural-networks","display_name":"graph neural networks","score":0.7289999723434448},{"id":"https://openalex.org/keywords/graph-representation-learning","display_name":"graph representation learning","score":0.47600001096725464}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7893999814987183},{"id":"https://openalex.org/C174348530","wikidata":"https://www.wikidata.org/wiki/Q188635","display_name":"Bridging (networking)","level":2,"score":0.5407999753952026},{"id":"https://openalex.org/C95623464","wikidata":"https://www.wikidata.org/wiki/Q1096149","display_name":"Classifier (UML)","level":2,"score":0.5205000042915344},{"id":"https://openalex.org/C132525143","wikidata":"https://www.wikidata.org/wiki/Q141488","display_name":"Graph","level":2,"score":0.5009999871253967},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4959999918937683},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4851999878883362},{"id":"https://openalex.org/C62611344","wikidata":"https://www.wikidata.org/wiki/Q1062658","display_name":"Node (physics)","level":2,"score":0.3425999879837036},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.3276999890804291},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.32760000228881836},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.2994000017642975},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.29919999837875366},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.28290000557899475},{"id":"https://openalex.org/C75564084","wikidata":"https://www.wikidata.org/wiki/Q5597085","display_name":"Graph embedding","level":3,"score":0.27799999713897705},{"id":"https://openalex.org/C59404180","wikidata":"https://www.wikidata.org/wiki/Q17013334","display_name":"Feature learning","level":2,"score":0.27709999680519104},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.2614000141620636},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.25850000977516174},{"id":"https://openalex.org/C2780598303","wikidata":"https://www.wikidata.org/wiki/Q65921492","display_name":"Flexibility (engineering)","level":2,"score":0.2565000057220459},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.2506999969482422}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.18653/v1/2026.findings-eacl.14","doi":"https://doi.org/10.18653/v1/2026.findings-eacl.14","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.findings-eacl.14","pdf_url":null,"source":{"id":"https://openalex.org/S7407087051","display_name":"Findings of the Association for Computational Linguistics: EACL","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"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: EACL 2026","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2410.02296","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2410.02296","pdf_url":"https://arxiv.org/pdf/2410.02296","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,"listed_in":[],"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":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2410.02296","doi":"https://doi.org/10.48550/arxiv.2410.02296","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2410.02296","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,"listed_in":[],"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"}],"best_oa_location":{"id":"doi:10.18653/v1/2026.findings-eacl.14","doi":"https://doi.org/10.18653/v1/2026.findings-eacl.14","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.findings-eacl.14","pdf_url":null,"source":{"id":"https://openalex.org/S7407087051","display_name":"Findings of the Association for Computational Linguistics: EACL","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"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: EACL 2026","raw_type":"proceedings-article"},"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":["https://openalex.org/W4387559293","https://openalex.org/W4393277515","https://openalex.org/W4412376898","https://openalex.org/W4391631706","https://openalex.org/W4407569655","https://openalex.org/W4412887821","https://openalex.org/W4410637068","https://openalex.org/W4409474941","https://openalex.org/W4412825844","https://openalex.org/W7090762342"],"abstract_inverted_index":{"Language":[0],"Models":[1],"(LMs)":[2],"are":[3,145],"increasingly":[4],"challenging":[5],"the":[6,56,70,110,154,166,180],"dominance":[7],"of":[8,66],"domain-specific":[9],"models,":[10],"such":[11],"as":[12],"Graph":[13,18],"Neural":[14],"Networks":[15],"(GNNs)":[16],"and":[17,81,98,107,144,160,171],"Transformers":[19],"(GTs),":[20],"in":[21],"graph":[22,174],"learning":[23,175],"tasks.":[24],"Following":[25],"this":[26,163],"trend,":[27],"we":[28,86],"propose":[29],"a":[30,63,115],"novel":[31],"approach":[32,61],"that":[33,119,130],"empowers":[34],"off-the-shelf":[35],"LMs":[36,133],"to":[37,41,72,147],"achieve":[38,84],"performance":[39],"comparable":[40,146],"state-of-the-art":[42],"(SOTA)":[43],"GNNs":[44],"on":[45,75,126],"node":[46,142,150,158],"classification":[47,112],"tasks,":[48],"without":[49],"requiring":[50],"any":[51],"architectural":[52],"modification.":[53],"By":[54,152],"preserving":[55],"LM's":[57],"original":[58],"architecture,":[59],"our":[60],"retains":[62],"key":[64,89],"benefit":[65],"LM":[67],"instruction":[68],"tuning:":[69],"ability":[71],"jointly":[73],"train":[74],"diverse":[76],"datasets,":[77],"fostering":[78],"greater":[79],"flexibility":[80],"efficiency.":[82],"To":[83],"this,":[85],"introduce":[87],"two":[88],"augmentation":[90,137],"strategies:":[91],"(1)":[92],"Enriching":[93],"LMs'":[94,111],"input":[95],"using":[96],"topological":[97],"semantic":[99],"retrieval":[100],"methods,":[101],"which":[102],"provide":[103],"richer":[104],"contextual":[105],"information,":[106],"(2)":[108],"guiding":[109],"process":[113],"through":[114],"lightweight":[116],"GNN":[117],"classifier":[118],"effectively":[120],"prunes":[121],"class":[122],"candidates.":[123],"Our":[124],"experiments":[125],"real-world":[127],"datasets":[128],"show":[129],"backbone":[131],"Flan-T5":[132],"equipped":[134],"with":[135],"these":[136],"strategies":[138],"outperform":[139],"SOTA":[140],"text-output":[141],"classifiers":[143,159],"top-performing":[148],"vector-output":[149],"classifiers.":[151],"bridging":[153],"gap":[155],"between":[156],"specialized":[157],"general":[161],"LMs,":[162],"work":[164],"paves":[165],"way":[167],"for":[168],"more":[169],"versatile":[170],"widely":[172],"applicable":[173],"models.":[176],"We":[177],"will":[178],"open-source":[179],"code":[181],"upon":[182],"publication.":[183]},"counts_by_year":[],"updated_date":"2026-10-12T09:40:04.860316","created_date":"2026-03-24T00:00:00"}