{"id":"https://openalex.org/W4400529822","doi":"https://doi.org/10.1145/3626772.3661384","title":"Large Language Models for Tabular Data: Progresses and Future Directions","display_name":"Large Language Models for Tabular Data: Progresses and Future Directions","publication_year":2024,"publication_date":"2024-07-10","ids":{"openalex":"https://openalex.org/W4400529822","doi":"https://doi.org/10.1145/3626772.3661384"},"language":"en","primary_location":{"id":"doi:10.1145/3626772.3661384","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3626772.3661384","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 47th International ACM SIGIR Conference on Research and Development in Information Retrieval","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5040829333","display_name":"Haoyu Dong","orcid":"https://orcid.org/0000-0003-0692-2228"},"institutions":[{"id":"https://openalex.org/I4210113369","display_name":"Microsoft Research Asia (China)","ror":"https://ror.org/0300m5276","country_code":"CN","type":"company","lineage":["https://openalex.org/I1290206253","https://openalex.org/I4210113369"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Haoyu Dong","raw_affiliation_strings":["Microsoft AI, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Microsoft AI, Beijing, China","institution_ids":["https://openalex.org/I4210113369"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5059929869","display_name":"Zhiruo Wang","orcid":"https://orcid.org/0000-0002-9839-8410"},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Zhiruo Wang","raw_affiliation_strings":["Carnegie Mellon University, Pittsburgh, PA, USA"],"affiliations":[{"raw_affiliation_string":"Carnegie Mellon University, Pittsburgh, PA, USA","institution_ids":["https://openalex.org/I74973139"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5040829333"],"corresponding_institution_ids":["https://openalex.org/I4210113369"],"apc_list":null,"apc_paid":null,"fwci":5.7641,"has_fulltext":false,"cited_by_count":16,"citation_normalized_percentile":{"value":0.96543349,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":94,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"2997","last_page":"3000"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.9998999834060669,"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":0.9998999834060669,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.9998000264167786,"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/T11719","display_name":"Data Quality and Management","score":0.9927999973297119,"subfield":{"id":"https://openalex.org/subfields/1803","display_name":"Management Science and Operations Research"},"field":{"id":"https://openalex.org/fields/18","display_name":"Decision Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7543364763259888},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.44618505239486694},{"id":"https://openalex.org/keywords/data-modeling","display_name":"Data modeling","score":0.41319525241851807},{"id":"https://openalex.org/keywords/data-science","display_name":"Data science","score":0.38797903060913086},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3694099187850952},{"id":"https://openalex.org/keywords/software-engineering","display_name":"Software engineering","score":0.17545470595359802}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7543364763259888},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.44618505239486694},{"id":"https://openalex.org/C67186912","wikidata":"https://www.wikidata.org/wiki/Q367664","display_name":"Data modeling","level":2,"score":0.41319525241851807},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.38797903060913086},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3694099187850952},{"id":"https://openalex.org/C115903868","wikidata":"https://www.wikidata.org/wiki/Q80993","display_name":"Software engineering","level":1,"score":0.17545470595359802}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3626772.3661384","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3626772.3661384","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 47th International ACM SIGIR Conference on Research and Development in Information Retrieval","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education","score":0.4099999964237213}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":33,"referenced_works":["https://openalex.org/W2048282669","https://openalex.org/W2138556038","https://openalex.org/W2290320465","https://openalex.org/W2341748398","https://openalex.org/W2398606196","https://openalex.org/W2518276024","https://openalex.org/W2888184422","https://openalex.org/W2898796029","https://openalex.org/W2899286282","https://openalex.org/W2913178646","https://openalex.org/W2914121031","https://openalex.org/W2963899988","https://openalex.org/W2999905431","https://openalex.org/W3008881932","https://openalex.org/W3035140194","https://openalex.org/W3098495697","https://openalex.org/W3099873751","https://openalex.org/W3102264439","https://openalex.org/W3103940211","https://openalex.org/W3167748596","https://openalex.org/W3193753157","https://openalex.org/W4221143046","https://openalex.org/W4230392236","https://openalex.org/W4230945824","https://openalex.org/W4281395820","https://openalex.org/W4386566488","https://openalex.org/W4389520779","https://openalex.org/W4404781897","https://openalex.org/W6600213211","https://openalex.org/W6600553734","https://openalex.org/W6602203279","https://openalex.org/W6602430550","https://openalex.org/W6602989878"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2748952813","https://openalex.org/W2390279801","https://openalex.org/W2358668433","https://openalex.org/W4396701345","https://openalex.org/W2376932109","https://openalex.org/W2001405890","https://openalex.org/W4396696052","https://openalex.org/W2382290278","https://openalex.org/W3204019825"],"abstract_inverted_index":{"Tables":[0],"contain":[1],"a":[2,145],"significant":[3,129],"portion":[4],"of":[5,79,87,122,128,148,164,196],"the":[6,50,77,85,120,126,149,186,193],"world's":[7],"structured":[8,47,137],"information.":[9,138],"The":[10],"ability":[11],"to":[12,45,76,119,143,180,191],"efficiently":[13],"and":[14,21,38,49,62,82,101,110,135,152,176,183,188],"accurately":[15,80],"understand,":[16],"process,":[17],"reason":[18],"about,":[19],"analyze,":[20],"generate":[22],"tabular":[23,123,159,199],"data":[24,124,200],"is":[25,72],"critical":[26],"for":[27,158,170,198],"achieving":[28],"Artificial":[29],"General":[30],"Intelligence":[31],"(AGI)":[32],"systems.":[33],"However,":[34],"despite":[35],"their":[36,46,202],"prevalence":[37],"importance,":[39],"tables":[40,66],"present":[41],"unique":[42],"challenges":[43],"due":[44,75],"nature":[48],"diverse":[51],"semantics":[52],"embedded":[53],"within":[54],"them.":[55],"Textual":[56],"content,":[57],"numerical":[58],"values,":[59],"visual":[60],"formats,":[61],"even":[63],"formulas":[64],"in":[65,96,108,131,154,201],"carry":[67],"rich":[68],"semantic":[69],"information":[70],"that":[71],"often":[73],"underutilized":[74],"complexity":[78],"interpreting":[81],"integrating.":[83],"Fortunately,":[84],"advent":[86],"Large":[88],"Language":[89],"Models":[90],"(LLMs)":[91],"has":[92],"opened":[93],"new":[94],"frontiers":[95],"natural":[97],"language":[98],"processing":[99],"(NLP)":[100],"machine":[102],"learning":[103],"(ML),":[104],"showing":[105],"remarkable":[106],"success":[107],"understanding":[109],"generating":[111],"text,":[112],"code,":[113],"etc.":[114],"Applying":[115],"these":[116],"advanced":[117],"models":[118],"domain":[121],"holds":[125],"promise":[127],"breakthroughs":[130],"how":[132],"we":[133,178],"process":[134],"leverage":[136],"Therefore,":[139],"this":[140],"tutorial":[141],"aims":[142],"provide":[144],"comprehensive":[146],"study":[147],"advances,":[150],"challenges,":[151],"opportunities":[153],"leveraging":[155],"cutting-edge":[156,168],"LLMs":[157,169,197],"data.":[160],"By":[161],"introducing":[162],"methods":[163],"prompting":[165],"or":[166],"training":[167],"table":[171],"interpreting,":[172],"processing,":[173],"reasoning,":[174],"analytics,":[175],"generation,":[177],"aim":[179],"equip":[181],"researchers":[182],"practitioners":[184],"with":[185],"knowledge":[187],"tools":[189],"needed":[190],"unlock":[192],"full":[194],"potential":[195],"domains.":[203]},"counts_by_year":[{"year":2026,"cited_by_count":3},{"year":2025,"cited_by_count":11},{"year":2024,"cited_by_count":2}],"updated_date":"2026-03-13T16:22:10.518609","created_date":"2025-10-10T00:00:00"}