{"id":"https://openalex.org/W7224078985","doi":"https://doi.org/10.48550/arxiv.2610.36806","title":"LLM knowledge for improved Out-of-Distribution Tabular Prediction - A Cross-Validated Regularisation Approach","display_name":"LLM knowledge for improved Out-of-Distribution Tabular Prediction - A Cross-Validated Regularisation Approach","publication_year":2026,"publication_date":"2026-10-27","ids":{"openalex":"https://openalex.org/W7224078985","doi":"https://doi.org/10.48550/arxiv.2610.36806"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2610.36806","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2610.36806","pdf_url":"https://arxiv.org/pdf/2610.36806","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"},"volume":null,"type":"preprint","indexed_in":["arxiv","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2610.36806","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5160005095","display_name":"S\u00f8lve Langseth","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I184531372","display_name":"OsloMet \u2013 Oslo Metropolitan University","ror":"https://ror.org/04q12yn84","country_code":"NO","type":"education","lineage":["https://openalex.org/I184531372"]}],"countries":["NO"],"is_corresponding":false,"raw_author_name":"Langseth, S\u00f8lve","raw_affiliation_strings":["Department of Computer Science , Oslo Metropolitan University , Oslo , Norway"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science , Oslo Metropolitan University , Oslo , Norway","institution_ids":["https://openalex.org/I184531372"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5066353327","display_name":"Kristoffer H. Hellton","orcid":"https://orcid.org/0000-0002-4779-486X","observed_orcids":["https://orcid.org/0000-0002-4779-486X"]},"institutions":[{"id":"https://openalex.org/I184531372","display_name":"OsloMet \u2013 Oslo Metropolitan University","ror":"https://ror.org/04q12yn84","country_code":"NO","type":"education","lineage":["https://openalex.org/I184531372"]}],"countries":["NO"],"is_corresponding":false,"raw_author_name":"Hellton, Kristoffer Herland","raw_affiliation_strings":["Department of Computer Science , Oslo Metropolitan University , Oslo , Norway"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science , Oslo Metropolitan University , Oslo , Norway","institution_ids":["https://openalex.org/I184531372"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5001144517","display_name":"Hugo L. Hammer","orcid":"https://orcid.org/0000-0001-9429-7148","observed_orcids":["https://orcid.org/0000-0001-9429-7148"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Hammer, Hugo L.","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"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":0.6083999872207642,"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":0.6083999872207642,"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/T12535","display_name":"Machine Learning and Data Classification","score":0.09120000153779984,"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":0.04450000077486038,"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/out-of-distribution-prediction","display_name":"out-of-distribution prediction","score":0.9580000042915344},{"id":"https://openalex.org/keywords/tabular-data","display_name":"tabular data","score":0.8690000176429749},{"id":"https://openalex.org/keywords/large-language-models","display_name":"large language models","score":0.9049999713897705},{"id":"https://openalex.org/keywords/expert-elicitation","display_name":"expert elicitation","score":0.8659999966621399},{"id":"https://openalex.org/keywords/shrinkage","display_name":"shrinkage","score":0.546999990940094},{"id":"https://openalex.org/keywords/domain-shift","display_name":"domain shift","score":0.6520000100135803},{"id":"https://openalex.org/keywords/cross-validation","display_name":"cross-validation","score":0.7279999852180481},{"id":"https://openalex.org/keywords/probabilistic-forecasting","display_name":"probabilistic forecasting","score":0.5099999904632568},{"id":"https://openalex.org/keywords/confidence-intervals","display_name":"confidence intervals","score":0.5740000009536743},{"id":"https://openalex.org/keywords/transfer-learning","display_name":"transfer learning","score":0.46799999475479126}],"concepts":[{"id":"https://openalex.org/C177769412","wikidata":"https://www.wikidata.org/wiki/Q278090","display_name":"Prior probability","level":3,"score":0.9581999778747559},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5512999892234802},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5327000021934509},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5160999894142151},{"id":"https://openalex.org/C49937458","wikidata":"https://www.wikidata.org/wiki/Q2599292","display_name":"Probabilistic logic","level":2,"score":0.5051000118255615},{"id":"https://openalex.org/C83546350","wikidata":"https://www.wikidata.org/wiki/Q1139051","display_name":"Regression","level":2,"score":0.492900013923645},{"id":"https://openalex.org/C81917197","wikidata":"https://www.wikidata.org/wiki/Q628760","display_name":"Selection (genetic algorithm)","level":2,"score":0.4733000099658966},{"id":"https://openalex.org/C139945424","wikidata":"https://www.wikidata.org/wiki/Q1940696","display_name":"Mean squared error","level":2,"score":0.45239999890327454},{"id":"https://openalex.org/C107673813","wikidata":"https://www.wikidata.org/wiki/Q812534","display_name":"Bayesian probability","level":2,"score":0.4138999879360199},{"id":"https://openalex.org/C2908647359","wikidata":"https://www.wikidata.org/wiki/Q2625603","display_name":"Population","level":2,"score":0.3635999858379364},{"id":"https://openalex.org/C3020402766","wikidata":"https://www.wikidata.org/wiki/Q104376712","display_name":"Prior information","level":2,"score":0.35760000348091125},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.3540000021457672},{"id":"https://openalex.org/C2778334786","wikidata":"https://www.wikidata.org/wiki/Q1586270","display_name":"Variation (astronomy)","level":2,"score":0.3537999987602234},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.34209999442100525},{"id":"https://openalex.org/C152877465","wikidata":"https://www.wikidata.org/wiki/Q208042","display_name":"Regression analysis","level":2,"score":0.34200000762939453},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.3375999927520752},{"id":"https://openalex.org/C102592046","wikidata":"https://www.wikidata.org/wiki/Q7504144","display_name":"Shrinkage estimator","level":5,"score":0.33169999718666077},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.3228999972343445},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3043000102043152},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.28679999709129333},{"id":"https://openalex.org/C149441793","wikidata":"https://www.wikidata.org/wiki/Q200726","display_name":"Probability distribution","level":2,"score":0.2809000015258789},{"id":"https://openalex.org/C160234255","wikidata":"https://www.wikidata.org/wiki/Q812535","display_name":"Bayesian inference","level":3,"score":0.27730000019073486},{"id":"https://openalex.org/C93959086","wikidata":"https://www.wikidata.org/wiki/Q6888345","display_name":"Model selection","level":2,"score":0.2644999921321869},{"id":"https://openalex.org/C103402496","wikidata":"https://www.wikidata.org/wiki/Q1106171","display_name":"Prediction interval","level":2,"score":0.26409998536109924},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.2574000060558319},{"id":"https://openalex.org/C2993060064","wikidata":"https://www.wikidata.org/wiki/Q49918","display_name":"Population mean","level":3,"score":0.2540999948978424}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2610.36806","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2610.36806","pdf_url":"https://arxiv.org/pdf/2610.36806","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.2610.36806","doi":"https://doi.org/10.48550/arxiv.2610.36806","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2610.36806","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":"pmh:oai:arXiv.org:2610.36806","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2610.36806","pdf_url":"https://arxiv.org/pdf/2610.36806","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"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7224078985.pdf","grobid_xml":"https://content.openalex.org/works/W7224078985.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W7125852452","https://openalex.org/W4402698565","https://openalex.org/W4405026151","https://openalex.org/W4416615488","https://openalex.org/W4402340041","https://openalex.org/W7215094760","https://openalex.org/W4392488103","https://openalex.org/W4403363997","https://openalex.org/W4307311424","https://openalex.org/W7172438149"],"abstract_inverted_index":{"Prediction":[0],"models":[1,40],"degrade":[2],"when":[3],"the":[4,9,47,97,110,125,142,156,162,167,185,192],"deployment":[5],"population":[6],"differs":[7],"from":[8,37],"one":[10],"used":[11],"to":[12,84,127],"train":[13],"them,":[14],"and":[15,29,67,90,118,204],"training":[16,186],"data":[17,187],"cannot":[18],"say":[19],"which":[20],"feature-response":[21],"relationships":[22],"will":[23],"transfer.":[24,201],"Expert":[25],"elicitation":[26],"is":[27,112],"slow":[28],"unscalable.":[30],"We":[31],"ask":[32],"whether":[33],"coefficient":[34],"priors":[35,75,123,140,203],"elicited":[36,197],"large":[38,189],"language":[39],"(LLMs)":[41],"improve":[42,200],"out-of-distribution":[43],"(OOD)":[44],"prediction":[45],"as":[46,172,174],"shrinkage":[48],"target":[49],"of":[50,55,79,92],"a":[51],"regularised":[52],"regression":[53],"instead":[54],"zero,":[56],"across":[57,138],"five":[58,80],"tabular":[59],"datasets":[60,166],"split":[61],"on":[62,77],"real":[63],"covariates,":[64],"selecting":[65],"providers":[66],"prior":[68,158,168],"structures":[69],"by":[70,82],"source-domain":[71],"cross-validation":[72,146],"alone.":[73],"The":[74],"help":[76],"four":[78],"datasets,":[81],"up":[83],"7.9%":[85],"OOD":[86],"mean":[87,98],"squared":[88],"error,":[89],"ten":[91],"twenty-four":[93],"prior-informed":[94],"results":[95],"resolve":[96],"improvement":[99],"at":[100],"conventional":[101],"confidence;":[102],"single-deployment":[103],"intervals":[104],"are":[105,188],"much":[106,173],"wider.":[107],"On":[108,164],"classification":[109],"gain":[111,194],"in":[113],"probabilistic":[114],"accuracy,":[115],"not":[116],"ranking,":[117],"control":[119],"tests":[120],"with":[121],"corrupted":[122],"attribute":[124],"benefit":[126],"feature-specific":[128],"content":[129],"rather":[130,159],"than":[131,160,180],"scale.":[132],"Two":[133],"findings":[134],"temper":[135],"this.":[136],"Variation":[137],"candidate":[139],"exceeds":[141],"average":[143],"benefit,":[144],"yet":[145],"margins":[147],"fall":[148],"below":[149],"their":[150],"own":[151],"noise,":[152],"so":[153],"selection":[154],"avoids":[155],"worst":[157],"finding":[161],"best.":[163],"three":[165],"improves":[169],"in-domain":[170,193],"accuracy":[171],"out-of-domain,":[175],"making":[176],"it":[177],"better":[178],"regularisation":[179],"shift":[181],"correction.":[182],"Only":[183],"where":[184],"enough":[190],"that":[191],"disappears":[195],"does":[196],"knowledge":[198],"demonstrably":[199],"Code,":[202],"results:":[205],"https://github.com/hugohammer/llm-priors-ood.":[206]},"counts_by_year":[],"updated_date":"2026-10-31T12:09:11.096373","created_date":"2026-10-29T00:00:00"}