{"id":"https://openalex.org/W7152425690","doi":"https://doi.org/10.1145/3774904.3792923","title":"Exploring Fine-Tuning for Tabular Foundation Models","display_name":"Exploring Fine-Tuning for Tabular Foundation Models","publication_year":2026,"publication_date":"2026-04-09","ids":{"openalex":"https://openalex.org/W7152425690","doi":"https://doi.org/10.1145/3774904.3792923"},"language":null,"primary_location":{"id":"doi:10.1145/3774904.3792923","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3774904.3792923","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the ACM Web Conference 2026","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.1145/3774904.3792923","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5123073445","display_name":"Aditya Tanna","orcid":null},"institutions":[{"id":"https://openalex.org/I154586514","display_name":"Lexmark (United States)","ror":"https://ror.org/00basdj35","country_code":"US","type":"company","lineage":["https://openalex.org/I154586514"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Aditya Tanna","raw_affiliation_strings":["Lexsi Labs, Mumbai, Maharashtra, India"],"raw_orcid":"https://orcid.org/0009-0000-1131-4062","affiliations":[{"raw_affiliation_string":"Lexsi Labs, Mumbai, Maharashtra, India","institution_ids":["https://openalex.org/I154586514"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5012713026","display_name":"Pratinav Seth","orcid":"https://orcid.org/0009-0001-4525-4464"},"institutions":[{"id":"https://openalex.org/I154586514","display_name":"Lexmark (United States)","ror":"https://ror.org/00basdj35","country_code":"US","type":"company","lineage":["https://openalex.org/I154586514"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Pratinav Seth","raw_affiliation_strings":["Lexsi Labs, Mumbai, Maharashtra, India"],"raw_orcid":"https://orcid.org/0009-0001-4525-4464","affiliations":[{"raw_affiliation_string":"Lexsi Labs, Mumbai, Maharashtra, India","institution_ids":["https://openalex.org/I154586514"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5099022862","display_name":"Mohamed Bouadi","orcid":"https://orcid.org/0009-0001-3905-0588"},"institutions":[{"id":"https://openalex.org/I154586514","display_name":"Lexmark (United States)","ror":"https://ror.org/00basdj35","country_code":"US","type":"company","lineage":["https://openalex.org/I154586514"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Mohamed Bouadi","raw_affiliation_strings":["Lexsi Labs, Paris, France"],"raw_orcid":"https://orcid.org/0009-0001-3905-0588","affiliations":[{"raw_affiliation_string":"Lexsi Labs, Paris, France","institution_ids":["https://openalex.org/I154586514"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5133258453","display_name":"Vinay Kumar Sankarapu","orcid":"https://orcid.org/0000-0002-9416-3497"},"institutions":[{"id":"https://openalex.org/I154586514","display_name":"Lexmark (United States)","ror":"https://ror.org/00basdj35","country_code":"US","type":"company","lineage":["https://openalex.org/I154586514"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Vinay Kumar Sankarapu","raw_affiliation_strings":["Lexsi Labs, London, United Kingdom"],"raw_orcid":"https://orcid.org/0000-0002-9416-3497","affiliations":[{"raw_affiliation_string":"Lexsi Labs, London, United Kingdom","institution_ids":["https://openalex.org/I154586514"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I154586514"],"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":"8613","last_page":"8616"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12100","display_name":"Advanced Mathematical Modeling in Engineering","score":0.06080000102519989,"subfield":{"id":"https://openalex.org/subfields/1703","display_name":"Computational Theory and Mathematics"},"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/T12100","display_name":"Advanced Mathematical Modeling in Engineering","score":0.06080000102519989,"subfield":{"id":"https://openalex.org/subfields/1703","display_name":"Computational Theory and Mathematics"},"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/T10233","display_name":"Geotechnical Engineering and Soil Mechanics","score":0.05079999938607216,"subfield":{"id":"https://openalex.org/subfields/2205","display_name":"Civil and Structural Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10996","display_name":"Computational Geometry and Mesh Generation","score":0.04309999942779541,"subfield":{"id":"https://openalex.org/subfields/1704","display_name":"Computer Graphics and Computer-Aided Design"},"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/foundation","display_name":"Foundation (evidence)","score":0.45750001072883606},{"id":"https://openalex.org/keywords/work","display_name":"Work (physics)","score":0.2572999894618988},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.23409999907016754},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.22759999334812164},{"id":"https://openalex.org/keywords/fuzzy-logic","display_name":"Fuzzy logic","score":0.22380000352859497}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.459199994802475},{"id":"https://openalex.org/C2780966255","wikidata":"https://www.wikidata.org/wiki/Q5474306","display_name":"Foundation (evidence)","level":2,"score":0.45750001072883606},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.2937999963760376},{"id":"https://openalex.org/C18762648","wikidata":"https://www.wikidata.org/wiki/Q42213","display_name":"Work (physics)","level":2,"score":0.2572999894618988},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.23409999907016754},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.23330000042915344},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.22759999334812164},{"id":"https://openalex.org/C58166","wikidata":"https://www.wikidata.org/wiki/Q224821","display_name":"Fuzzy logic","level":2,"score":0.22380000352859497},{"id":"https://openalex.org/C116834253","wikidata":"https://www.wikidata.org/wiki/Q2039217","display_name":"Identification (biology)","level":2,"score":0.2102999985218048},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.2062000036239624}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3774904.3792923","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3774904.3792923","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the ACM Web Conference 2026","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3774904.3792923","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3774904.3792923","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the ACM Web Conference 2026","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":2,"referenced_works":["https://openalex.org/W4382202657","https://openalex.org/W4406170795"],"related_works":[],"abstract_inverted_index":{"Tabular":[0],"Foundation":[1],"Models":[2],"(TFMs)":[3],"have":[4],"recently":[5],"shown":[6],"strong":[7,30],"in-context":[8],"learning":[9,21],"capabilities":[10],"on":[11,111],"structured":[12],"data,":[13],"achieving":[14],"zero-shot":[15,26],"performance":[16],"comparable":[17],"to":[18],"traditional":[19],"machine":[20],"methods.":[22],"We":[23,79],"find":[24],"that":[25],"TFMs":[27,71],"already":[28],"achieve":[29],"performance,":[31,104],"while":[32],"the":[33,64],"benefits":[34],"of":[35,68],"fine-tuning":[36,54,69,113],"are":[37],"highly":[38],"model-":[39],"and":[40,43,77,85,97,106,117],"data-dependent.":[41],"Meta-learning":[42],"PEFT":[44],"provide":[45],"moderate":[46],"gains":[47],"under":[48],"specific":[49],"conditions,":[50],"whereas":[51],"full":[52],"supervised":[53,83],"often":[55],"reduces":[56],"accuracy":[57],"or":[58],"calibration":[59],"quality.":[60],"This":[61],"work":[62],"presents":[63],"first":[65],"comprehensive":[66],"study":[67],"in":[70],"across":[72],"benchmarks":[73],"including":[74],"TALENT,":[75],"OpenML-CC18,":[76],"TabZilla.":[78],"compare":[80],"zero-shot,":[81],"meta-learning,":[82],"(SFT),":[84],"parameter-efficient":[86],"(PEFT)":[87],"approaches,":[88],"analyzing":[89],"how":[90],"dataset":[91],"factors":[92],"such":[93],"as":[94],"imbalance,":[95],"size,":[96],"dimensionality":[98],"affect":[99],"outcomes.":[100],"Our":[101],"findings":[102],"cover":[103],"calibration,":[105],"fairness,":[107],"offering":[108],"practical":[109],"guidelines":[110],"when":[112],"is":[114],"most":[115],"beneficial":[116],"its":[118],"limitations.":[119]},"counts_by_year":[],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2026-04-10T00:00:00"}