{"id":"https://openalex.org/W7164411758","doi":"https://doi.org/10.48550/arxiv.2606.11640","title":"TAROT: Task-Adaptive Refinement of LLM-prior Graphs for Few-shot Tabular Learning","display_name":"TAROT: Task-Adaptive Refinement of LLM-prior Graphs for Few-shot Tabular Learning","publication_year":2026,"publication_date":"2026-06-10","ids":{"openalex":"https://openalex.org/W7164411758","doi":"https://doi.org/10.48550/arxiv.2606.11640"},"language":null,"primary_location":{"id":"doi:10.48550/arxiv.2606.11640","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2606.11640","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.2606.11640","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5138415039","display_name":"Ruxue Shi","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Shi, Ruxue","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5138465673","display_name":"Yili Wang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wang, Yili","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5138420700","display_name":"Mengnan Du","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Du, Mengnan","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5055076829","display_name":"Hangting Ye","orcid":"https://orcid.org/0000-0001-6920-4181"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ye, Hangting","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5138396457","display_name":"Yi Chang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Chang, Yi","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5138433129","display_name":"Xin Wang (91924)","orcid":"https://orcid.org/0000-0001-9607-7763"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wang, Xin","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/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.5108000040054321,"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/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.5108000040054321,"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/T11689","display_name":"Adversarial Robustness in Machine Learning","score":0.10090000182390213,"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/T11273","display_name":"Advanced Graph Neural Networks","score":0.0658000037074089,"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/graph","display_name":"Graph","score":0.6133000254631042},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.4185999929904938},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.41519999504089355},{"id":"https://openalex.org/keywords/semantics","display_name":"Semantics (computer science)","score":0.3765999972820282},{"id":"https://openalex.org/keywords/semantic-feature","display_name":"Semantic feature","score":0.3741999864578247},{"id":"https://openalex.org/keywords/semantic-similarity","display_name":"Semantic similarity","score":0.37400001287460327},{"id":"https://openalex.org/keywords/annotation","display_name":"Annotation","score":0.3711000084877014},{"id":"https://openalex.org/keywords/semantic-computing","display_name":"Semantic computing","score":0.350600004196167},{"id":"https://openalex.org/keywords/attention-network","display_name":"Attention network","score":0.3495999872684479}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7806000113487244},{"id":"https://openalex.org/C132525143","wikidata":"https://www.wikidata.org/wiki/Q141488","display_name":"Graph","level":2,"score":0.6133000254631042},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.43619999289512634},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.4185999929904938},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.41519999504089355},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.3765999972820282},{"id":"https://openalex.org/C2781122975","wikidata":"https://www.wikidata.org/wiki/Q16928266","display_name":"Semantic feature","level":2,"score":0.3741999864578247},{"id":"https://openalex.org/C130318100","wikidata":"https://www.wikidata.org/wiki/Q2268914","display_name":"Semantic similarity","level":2,"score":0.37400001287460327},{"id":"https://openalex.org/C2776321320","wikidata":"https://www.wikidata.org/wiki/Q857525","display_name":"Annotation","level":2,"score":0.3711000084877014},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.36559998989105225},{"id":"https://openalex.org/C511149849","wikidata":"https://www.wikidata.org/wiki/Q7449051","display_name":"Semantic computing","level":3,"score":0.350600004196167},{"id":"https://openalex.org/C2993807640","wikidata":"https://www.wikidata.org/wiki/Q103709453","display_name":"Attention network","level":2,"score":0.3495999872684479},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.34459999203681946},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.3409999907016754},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.3377000093460083},{"id":"https://openalex.org/C97256817","wikidata":"https://www.wikidata.org/wiki/Q1462316","display_name":"Spurious relationship","level":2,"score":0.33500000834465027},{"id":"https://openalex.org/C90312973","wikidata":"https://www.wikidata.org/wiki/Q7449052","display_name":"Semantic data model","level":2,"score":0.3287000060081482},{"id":"https://openalex.org/C62611344","wikidata":"https://www.wikidata.org/wiki/Q1062658","display_name":"Node (physics)","level":2,"score":0.301800012588501},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.29980000853538513},{"id":"https://openalex.org/C165064840","wikidata":"https://www.wikidata.org/wiki/Q1321061","display_name":"Matching (statistics)","level":2,"score":0.29910001158714294},{"id":"https://openalex.org/C146380142","wikidata":"https://www.wikidata.org/wiki/Q1137726","display_name":"Directed graph","level":2,"score":0.2912999987602234},{"id":"https://openalex.org/C2778493491","wikidata":"https://www.wikidata.org/wiki/Q7449072","display_name":"Semantic matching","level":3,"score":0.29120001196861267},{"id":"https://openalex.org/C85407183","wikidata":"https://www.wikidata.org/wiki/Q1045785","display_name":"Semantic network","level":2,"score":0.2890999913215637},{"id":"https://openalex.org/C197914299","wikidata":"https://www.wikidata.org/wiki/Q18650","display_name":"Semantic memory","level":3,"score":0.2831999957561493},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.27379998564720154},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.2678000032901764},{"id":"https://openalex.org/C2987255567","wikidata":"https://www.wikidata.org/wiki/Q33002955","display_name":"Knowledge graph","level":2,"score":0.26759999990463257},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.26579999923706055},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.2635999917984009},{"id":"https://openalex.org/C132964779","wikidata":"https://www.wikidata.org/wiki/Q2110223","display_name":"Raw data","level":2,"score":0.26010000705718994},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.25220000743865967},{"id":"https://openalex.org/C155846161","wikidata":"https://www.wikidata.org/wiki/Q1143367","display_name":"Graphical model","level":2,"score":0.25049999356269836}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2606.11640","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2606.11640","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.2606.11640","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2606.11640","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":{"Few-shot":[0],"tabular":[1,58,134,140,236],"learning":[2,237],"provides":[3],"a":[4,86,107,121,148,176,215,248],"cost-effective":[5],"approach":[6,250],"for":[7,18,84,93,229],"real-world":[8],"applications":[9],"where":[10],"annotation":[11],"is":[12,21,91],"costly":[13],"and":[14,25,64,81,114,119,171,201],"collecting":[15],"sufficient":[16],"samples":[17],"new":[19],"tasks":[20],"difficult.":[22],"Existing":[23],"Traditional":[24],"LLM-based":[26,52],"methods":[27,36,53],"have":[28],"demonstrated":[29],"effectiveness":[30],"in":[31,98,132,251],"few-shot":[32,99,133,235],"scenarios.":[33,100],"However,":[34],"traditional":[35],"need":[37],"additional":[38],"training":[39],"on":[40,167,233],"unlabeled":[41],"or":[42,198],"generated":[43],"data,":[44],"which":[45,78],"incur":[46],"significant":[47],"computational":[48],"overhead.":[49],"In":[50,101],"addition,":[51],"that":[54,110,195],"directly":[55],"feed":[56],"raw":[57],"data":[59,141],"into":[60,142],"LLMs":[61,158],"raise":[62],"privacy":[63],"compliance":[65],"concerns.":[66],"More":[67],"importantly,":[68],"both":[69],"paradigms":[70],"largely":[71],"overlook":[72],"the":[73,112,161,168,185,207,211,221,240],"semantic":[74,82,87,115,123,145,162,177,227],"relationships":[75],"between":[76,164],"features,":[77],"provide":[79],"structural":[80,113,181],"prior":[83,116],"constructing":[85,118],"graph.":[88,178],"Semantic":[89,150,192],"graph":[90,124,208,223],"essential":[92],"modeling":[94],"meaningful":[95],"feature":[96,172],"interactions":[97],"this":[102,126,252],"paper,":[103],"we":[104],"propose":[105],"TAROT,":[106,244],"GNN-based":[108],"framework":[109],"encodes":[111,138],"by":[117,184],"refining":[120],"task-adaptive":[122],"from":[125],"prior,":[127],"thereby":[128],"improving":[129],"predictive":[130],"performance":[131,242],"learning.":[135],"TAROT":[136,189],"first":[137],"heterogeneous":[139],"unified":[143],"node":[144],"representations":[146],"via":[147],"Unified":[149],"Tabular":[151],"Node":[152],"Encoder":[153],"(USTNE).":[154],"Then,":[155],"it":[156,246],"prompts":[157],"to":[159,174,224],"infer":[160],"relationship":[163],"features":[165],"based":[166],"task":[169],"description":[170],"names":[173],"construct":[175],"To":[179],"mitigate":[180],"noise":[182],"introduced":[183],"hallucination":[186],"of":[187,243],"LLMs,":[188],"introduces":[190],"Task-adaptive":[191],"Graph":[193],"Refinement":[194],"prunes":[196],"spurious":[197],"task-unrelated":[199],"edges":[200],"adds":[202],"missing":[203],"task-related":[204,226],"ones,":[205],"aligning":[206],"structure":[209],"with":[210],"downstream":[212],"objective.":[213],"Finally,":[214],"GNN":[216],"performs":[217],"message":[218],"passing":[219],"over":[220],"refined":[222],"capture":[225],"dependencies":[228],"prediction.":[230],"Extensive":[231],"experiments":[232],"various":[234],"benchmarks":[238],"demonstrate":[239],"superior":[241],"establishing":[245],"as":[247],"state-of-the-art":[249],"domain.":[253]},"counts_by_year":[],"updated_date":"2026-07-28T07:46:37.118299","created_date":"2026-06-12T00:00:00"}