{"id":"https://openalex.org/W7139123741","doi":"https://doi.org/10.48550/arxiv.2603.17737","title":"Embedding World Knowledge into Tabular Models: Towards Best Practices for Embedding Pipeline Design","display_name":"Embedding World Knowledge into Tabular Models: Towards Best Practices for Embedding Pipeline Design","publication_year":2026,"publication_date":"2026-03-18","ids":{"openalex":"https://openalex.org/W7139123741","doi":"https://doi.org/10.48550/arxiv.2603.17737"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2603.17737","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2603.17737","pdf_url":"https://arxiv.org/pdf/2603.17737","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":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"parent_works":[],"lineage":["https://openalex.org/W7139123741"],"child_works_count":0,"type":"preprint","is_traditional":true,"indexed_in":["arxiv","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2603.17737","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5129890246","display_name":"Oksana Kolomenko","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I122228004","display_name":"HTW Berlin - University of Applied Sciences","ror":"https://ror.org/01xzwj424","country_code":"DE","type":"education","lineage":["https://openalex.org/I122228004"]},{"id":"https://openalex.org/I129643931","display_name":"Berliner Hochschule f\u00fcr Technik","ror":"https://ror.org/00w7whj55","country_code":"DE","type":"education","lineage":["https://openalex.org/I129643931"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Kolomenko, Oksana","raw_affiliation_strings":["KI-Werkstatt , University of Applied Sciences Berlin HTW Berlin , 10313 Berlin , Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"KI-Werkstatt , University of Applied Sciences Berlin HTW Berlin , 10313 Berlin , Germany","institution_ids":["https://openalex.org/I122228004","https://openalex.org/I129643931"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5063957903","display_name":"Ricardo Knauer","orcid":"https://orcid.org/0009-0003-9258-5105","observed_orcids":["https://orcid.org/0009-0003-9258-5105"]},"institutions":[{"id":"https://openalex.org/I122228004","display_name":"HTW Berlin - University of Applied Sciences","ror":"https://ror.org/01xzwj424","country_code":"DE","type":"education","lineage":["https://openalex.org/I122228004"]},{"id":"https://openalex.org/I129643931","display_name":"Berliner Hochschule f\u00fcr Technik","ror":"https://ror.org/00w7whj55","country_code":"DE","type":"education","lineage":["https://openalex.org/I129643931"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Knauer, Ricardo","raw_affiliation_strings":["KI-Werkstatt , University of Applied Sciences Berlin HTW Berlin , 10313 Berlin , Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"KI-Werkstatt , University of Applied Sciences Berlin HTW Berlin , 10313 Berlin , Germany","institution_ids":["https://openalex.org/I122228004","https://openalex.org/I129643931"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5018098456","display_name":"Erik Rodner","orcid":"https://orcid.org/0000-0002-3711-1498","observed_orcids":["https://orcid.org/0000-0002-3711-1498"]},"institutions":[{"id":"https://openalex.org/I122228004","display_name":"HTW Berlin - University of Applied Sciences","ror":"https://ror.org/01xzwj424","country_code":"DE","type":"education","lineage":["https://openalex.org/I122228004"]},{"id":"https://openalex.org/I129643931","display_name":"Berliner Hochschule f\u00fcr Technik","ror":"https://ror.org/00w7whj55","country_code":"DE","type":"education","lineage":["https://openalex.org/I129643931"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Rodner, Erik","raw_affiliation_strings":["KI-Werkstatt , University of Applied Sciences Berlin HTW Berlin , 10313 Berlin , Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"KI-Werkstatt , University of Applied Sciences Berlin HTW Berlin , 10313 Berlin , Germany","institution_ids":["https://openalex.org/I122228004","https://openalex.org/I129643931"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":2,"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/T10028","display_name":"Topic Modeling","score":0.37209999561309814,"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/T10028","display_name":"Topic Modeling","score":0.37209999561309814,"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":0.1428000032901764,"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":0.07970000058412552,"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/large-language-models","display_name":"large language models","score":0.9419999718666077},{"id":"https://openalex.org/keywords/world-knowledge","display_name":"world knowledge","score":0.5540000200271606},{"id":"https://openalex.org/keywords/gradient-boosted-decision-trees","display_name":"gradient boosting decision tree","score":0.8410000205039978},{"id":"https://openalex.org/keywords/benchmarking","display_name":"benchmarking","score":0.4020000100135803}],"concepts":[{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.8580999970436096},{"id":"https://openalex.org/C43521106","wikidata":"https://www.wikidata.org/wiki/Q2165493","display_name":"Pipeline (software)","level":2,"score":0.7379000186920166},{"id":"https://openalex.org/C34736171","wikidata":"https://www.wikidata.org/wiki/Q918333","display_name":"Preprocessor","level":2,"score":0.6401000022888184},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6284999847412109},{"id":"https://openalex.org/C2780586970","wikidata":"https://www.wikidata.org/wiki/Q1357284","display_name":"Popularity","level":2,"score":0.5889999866485596},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.49399998784065247},{"id":"https://openalex.org/C2776207758","wikidata":"https://www.wikidata.org/wiki/Q5303302","display_name":"Downstream (manufacturing)","level":2,"score":0.491100013256073},{"id":"https://openalex.org/C175309249","wikidata":"https://www.wikidata.org/wiki/Q725864","display_name":"Pipeline transport","level":2,"score":0.48559999465942383},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.48429998755455017},{"id":"https://openalex.org/C184356942","wikidata":"https://www.wikidata.org/wiki/Q830382","display_name":"Best practice","level":2,"score":0.48399999737739563},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.453900009393692},{"id":"https://openalex.org/C46686674","wikidata":"https://www.wikidata.org/wiki/Q466303","display_name":"Boosting (machine learning)","level":2,"score":0.4406999945640564},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.3310999870300293},{"id":"https://openalex.org/C10551718","wikidata":"https://www.wikidata.org/wiki/Q5227332","display_name":"Data pre-processing","level":2,"score":0.29089999198913574},{"id":"https://openalex.org/C70153297","wikidata":"https://www.wikidata.org/wiki/Q5591907","display_name":"Gradient boosting","level":3,"score":0.26899999380111694},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.25929999351501465},{"id":"https://openalex.org/C45804977","wikidata":"https://www.wikidata.org/wiki/Q7239673","display_name":"Predictive modelling","level":2,"score":0.2547000050544739},{"id":"https://openalex.org/C134121241","wikidata":"https://www.wikidata.org/wiki/Q899301","display_name":"Yield (engineering)","level":2,"score":0.2526000142097473}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2603.17737","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2603.17737","pdf_url":"https://arxiv.org/pdf/2603.17737","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":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2603.17737","doi":"https://doi.org/10.48550/arxiv.2603.17737","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2603.17737","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":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2603.17737","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2603.17737","pdf_url":"https://arxiv.org/pdf/2603.17737","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":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7139123741.pdf","grobid_xml":"https://content.openalex.org/works/W7139123741.grobid-xml"},"referenced_works_count":7,"referenced_works":["https://openalex.org/W4283318146","https://openalex.org/W4389911749","https://openalex.org/W4403579392","https://openalex.org/W4404354131","https://openalex.org/W4407569679","https://openalex.org/W4407719151","https://openalex.org/W4414987631"],"related_works":["https://openalex.org/W7160515951","https://openalex.org/W7135081562","https://openalex.org/W7163042746","https://openalex.org/W4416615488","https://openalex.org/W4407719151","https://openalex.org/W4392488103","https://openalex.org/W4367189670","https://openalex.org/W7155550139","https://openalex.org/W7221801823","https://openalex.org/W4416019989"],"abstract_inverted_index":{"Embeddings":[0],"are":[1,107],"a":[2],"powerful":[3],"way":[4],"to":[5,27,84,96,117],"enrich":[6],"data-driven":[7],"machine":[8],"learning":[9],"models":[10,18,94],"with":[11,90,128],"the":[12,64,70,76,87],"world":[13],"knowledge":[14,72],"of":[15,73],"large":[16],"language":[17],"(LLMs).":[19],"Yet,":[20],"there":[21],"is":[22],"limited":[23],"evidence":[24],"on":[25,63],"how":[26],"design":[28,67],"effective":[29,133],"LLM-based":[30],"embedding":[31,50,93,134],"pipelines":[32,135],"for":[33,130,136],"tabular":[34,137],"prediction.":[35],"In":[36,79],"this":[37],"work,":[38],"we":[39],"systematically":[40],"benchmark":[41],"256":[42],"pipeline":[43,66],"configurations,":[44],"covering":[45],"8":[46],"preprocessing":[47],"strategies,":[48],"16":[49],"models,":[51],"and":[52,104,126],"2":[53],"downstream":[54,120],"models.":[55,121],"Our":[56,122],"results":[57],"show":[58],"that":[59],"it":[60],"strongly":[61],"depends":[62],"specific":[65],"whether":[68],"incorporating":[69],"prior":[71],"LLMs":[74],"improves":[75],"predictive":[77],"performance.":[78],"general,":[80],"concatenating":[81],"embeddings":[82],"tends":[83],"outperform":[85],"replacing":[86],"original":[88],"columns":[89],"embeddings.":[91],"Larger":[92],"tend":[95,116],"yield":[97],"better":[98],"results,":[99],"while":[100],"public":[101],"leaderboard":[102],"rankings":[103],"model":[105],"popularity":[106],"poor":[108],"performance":[109],"indicators.":[110],"Finally,":[111],"gradient":[112],"boosting":[113],"decision":[114],"trees":[115],"be":[118],"strong":[119],"findings":[123],"provide":[124],"researchers":[125],"practitioners":[127],"guidance":[129],"building":[131],"more":[132],"prediction":[138],"tasks.":[139]},"counts_by_year":[{"year":2026,"cited_by_count":2}],"updated_date":"2026-11-07T11:25:07.637180","created_date":"2025-11-06T00:00:00"}