{"id":"https://openalex.org/W7124712466","doi":"https://doi.org/10.48550/arxiv.2601.11311","title":"FORESTLLM: Large Language Models Make Random Forest Great on Few-shot Tabular Learning","display_name":"FORESTLLM: Large Language Models Make Random Forest Great on Few-shot Tabular Learning","publication_year":2026,"publication_date":"2026-01-16","ids":{"openalex":"https://openalex.org/W7124712466","doi":"https://doi.org/10.48550/arxiv.2601.11311"},"language":null,"primary_location":{"id":"doi:10.48550/arxiv.2601.11311","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2601.11311","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"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":"article"},"type":"preprint","indexed_in":["datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://doi.org/10.48550/arxiv.2601.11311","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5123321136","display_name":"Zhihan Yang","orcid":null},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Yang, Zhihan","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5123357241","display_name":"Jiaqi Wei","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wei, Jiaqi","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5123347262","display_name":"Xiang Zhang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhang, Xiang","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5123316242","display_name":"Haoyu Dong","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Dong, Haoyu","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5123289807","display_name":"Yiwen Wang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wang, Yiwen","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5123337789","display_name":"Xiaoke Guo","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Guo, Xiaoke","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5123348652","display_name":"Pengkun Zhang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhang, Pengkun","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5123339454","display_name":"Yiwei Xu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xu, Yiwei","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5122238409","display_name":"Chenyu You","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"You, Chenyu","raw_affiliation_strings":[],"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":9,"corresponding_author_ids":["https://openalex.org/A5123321136"],"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/T13702","display_name":"Machine Learning in Healthcare","score":0.17759999632835388,"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/T13702","display_name":"Machine Learning in Healthcare","score":0.17759999632835388,"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/T12026","display_name":"Explainable Artificial Intelligence (XAI)","score":0.15070000290870667,"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/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.08900000154972076,"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/overfitting","display_name":"Overfitting","score":0.7688999772071838},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.5928000211715698},{"id":"https://openalex.org/keywords/random-forest","display_name":"Random forest","score":0.49149999022483826},{"id":"https://openalex.org/keywords/decision-tree","display_name":"Decision tree","score":0.42489999532699585},{"id":"https://openalex.org/keywords/semantics","display_name":"Semantics (computer science)","score":0.4221999943256378},{"id":"https://openalex.org/keywords/coherence","display_name":"Coherence (philosophical gambling strategy)","score":0.40950000286102295},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.3774999976158142},{"id":"https://openalex.org/keywords/path","display_name":"Path (computing)","score":0.3659000098705292}],"concepts":[{"id":"https://openalex.org/C22019652","wikidata":"https://www.wikidata.org/wiki/Q331309","display_name":"Overfitting","level":3,"score":0.7688999772071838},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7566999793052673},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6467000246047974},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.6376000046730042},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.5928000211715698},{"id":"https://openalex.org/C169258074","wikidata":"https://www.wikidata.org/wiki/Q245748","display_name":"Random forest","level":2,"score":0.49149999022483826},{"id":"https://openalex.org/C84525736","wikidata":"https://www.wikidata.org/wiki/Q831366","display_name":"Decision tree","level":2,"score":0.42489999532699585},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.4221999943256378},{"id":"https://openalex.org/C2781181686","wikidata":"https://www.wikidata.org/wiki/Q4226068","display_name":"Coherence (philosophical gambling strategy)","level":2,"score":0.40950000286102295},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.3774999976158142},{"id":"https://openalex.org/C2777735758","wikidata":"https://www.wikidata.org/wiki/Q817765","display_name":"Path (computing)","level":2,"score":0.3659000098705292},{"id":"https://openalex.org/C62611344","wikidata":"https://www.wikidata.org/wiki/Q1062658","display_name":"Node (physics)","level":2,"score":0.35580000281333923},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.3553999960422516},{"id":"https://openalex.org/C79581498","wikidata":"https://www.wikidata.org/wiki/Q1367530","display_name":"Suite","level":2,"score":0.3368000090122223},{"id":"https://openalex.org/C113174947","wikidata":"https://www.wikidata.org/wiki/Q2859736","display_name":"Tree (set theory)","level":2,"score":0.311599999666214},{"id":"https://openalex.org/C114289077","wikidata":"https://www.wikidata.org/wiki/Q3284399","display_name":"Statistical model","level":2,"score":0.2930999994277954},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.2856000065803528},{"id":"https://openalex.org/C136389625","wikidata":"https://www.wikidata.org/wiki/Q334384","display_name":"Supervised learning","level":3,"score":0.28459998965263367},{"id":"https://openalex.org/C155846161","wikidata":"https://www.wikidata.org/wiki/Q1143367","display_name":"Graphical model","level":2,"score":0.2721000015735626},{"id":"https://openalex.org/C67186912","wikidata":"https://www.wikidata.org/wiki/Q367664","display_name":"Data modeling","level":2,"score":0.25859999656677246},{"id":"https://openalex.org/C158600405","wikidata":"https://www.wikidata.org/wiki/Q5054566","display_name":"Causal inference","level":2,"score":0.25200000405311584}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2601.11311","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2601.11311","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"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":"article"}],"best_oa_location":{"id":"doi:10.48550/arxiv.2601.11311","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2601.11311","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"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":"article"},"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":{"Tabular":[0],"data":[1,19],"high-stakes":[2],"critical":[3],"decision-making":[4],"in":[5,20,37,150],"domains":[6],"such":[7],"as":[8,114],"finance,":[9],"healthcare,":[10],"and":[11,51,164,173,199,223],"scientific":[12],"discovery.":[13],"Yet,":[14],"learning":[15],"effectively":[16],"from":[17],"tabular":[18],"few-shot":[21,178,221],"settings,":[22],"where":[23,192],"labeled":[24,163],"examples":[25,202],"are":[26],"scarce,":[27],"remains":[28],"a":[29,85,125,146,183,204,217],"fundamental":[30],"challenge.":[31],"Traditional":[32],"tree-based":[33],"methods":[34],"often":[35,69],"falter":[36],"these":[38,80],"regimes":[39],"due":[40],"to":[41,53,75],"their":[42,159],"reliance":[43],"on":[44,158],"statistical":[45],"purity":[46],"metrics,":[47],"which":[48,151],"become":[49],"unstable":[50],"prone":[52],"overfitting":[54],"with":[55,97,212],"limited":[56],"supervision.":[57,179],"At":[58],"the":[59,90,98,107,131,152,168,193,196],"same":[60],"time,":[61],"direct":[62],"applications":[63],"of":[64,94,102,170,220],"large":[65],"language":[66],"models":[67],"(LLMs)":[68],"overlook":[70],"its":[71,200],"inherent":[72],"structure,":[73],"leading":[74],"suboptimal":[76],"performance.":[77,229],"To":[78],"overcome":[79],"limitations,":[81],"we":[82,144,181],"propose":[83,182],"FORESTLLM,":[84],"novel":[86],"framework":[87],"that":[88,119],"unifies":[89],"structural":[91],"inductive":[92],"biases":[93],"decision":[95,197],"forests":[96],"semantic":[99,147],"reasoning":[100],"capabilities":[101],"LLMs.":[103],"Crucially,":[104],"FORESTLLM":[105,226],"leverages":[106],"LLM":[108,134,153,194],"only":[109],"during":[110],"training,":[111],"treating":[112],"it":[113],"an":[115],"offline":[116],"model":[117],"designer":[118],"encodes":[120],"rich,":[121],"contextual":[122],"knowledge":[123],"into":[124,203],"lightweight,":[126],"interpretable":[127],"forest":[128],"model,":[129],"eliminating":[130],"need":[132],"for":[133,188],"inference":[135,186],"at":[136],"test":[137],"time.":[138],"Our":[139],"method":[140],"is":[141],"two-fold.":[142],"First,":[143],"introduce":[145],"splitting":[148],"criterion":[149],"evaluates":[154],"candidate":[155],"partitions":[156],"based":[157],"coherence":[160],"over":[161],"both":[162],"unlabeled":[165],"data,":[166],"enabling":[167],"induction":[169],"more":[171],"robust":[172],"generalizable":[174],"tree":[175],"structures":[176],"under":[177],"Second,":[180],"one-time":[184],"in-context":[185],"mechanism":[187],"leaf":[189],"node":[190],"stabilization,":[191],"distills":[195],"path":[198],"supporting":[201],"concise,":[205],"deterministic":[206],"prediction,":[207],"replacing":[208],"noisy":[209],"empirical":[210],"estimates":[211],"semantically":[213],"informed":[214],"outputs.":[215],"Across":[216],"diverse":[218],"suite":[219],"classification":[222],"regression":[224],"benchmarks,":[225],"achieves":[227],"state-of-the-art":[228]},"counts_by_year":[],"updated_date":"2026-01-20T17:29:24.968406","created_date":"2026-01-20T00:00:00"}