{"id":"https://openalex.org/W4412888395","doi":"https://doi.org/10.18653/v1/2025.findings-acl.381","title":"TableDreamer: Progressive and Weakness-guided Data Synthesis from Scratch for Table Instruction Tuning","display_name":"TableDreamer: Progressive and Weakness-guided Data Synthesis from Scratch for Table Instruction Tuning","publication_year":2025,"publication_date":"2025-01-01","ids":{"openalex":"https://openalex.org/W4412888395","doi":"https://doi.org/10.18653/v1/2025.findings-acl.381"},"language":"en","primary_location":{"id":"doi:10.18653/v1/2025.findings-acl.381","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.findings-acl.381","pdf_url":"https://aclanthology.org/2025.findings-acl.381.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Findings of the Association for Computational Linguistics: ACL 2025","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://aclanthology.org/2025.findings-acl.381.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5014223736","display_name":"Mingyu Zheng","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Mingyu Zheng","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5105687411","display_name":"Zhifan Feng","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhifan Feng","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100872968","display_name":"Jia Wang","orcid":"https://orcid.org/0009-0005-0516-5183"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jia Wang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5087617391","display_name":"Lanrui Wang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Lanrui Wang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5067997634","display_name":"Zheng Lin","orcid":"https://orcid.org/0000-0002-8432-1658"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zheng Lin","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102002749","display_name":"Hao Yang","orcid":"https://orcid.org/0000-0002-8013-9023"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Hao Yang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5100442319","display_name":"Weiping Wang","orcid":"https://orcid.org/0000-0002-6796-7596"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Weiping Wang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.20118955,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"7290","last_page":"7315"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12720","display_name":"Multimedia Communication and Technology","score":0.8216000199317932,"subfield":{"id":"https://openalex.org/subfields/3312","display_name":"Sociology and Political Science"},"field":{"id":"https://openalex.org/fields/33","display_name":"Social Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},"topics":[{"id":"https://openalex.org/T12720","display_name":"Multimedia Communication and Technology","score":0.8216000199317932,"subfield":{"id":"https://openalex.org/subfields/3312","display_name":"Sociology and Political Science"},"field":{"id":"https://openalex.org/fields/33","display_name":"Social Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/scratch","display_name":"Scratch","score":0.6890825629234314},{"id":"https://openalex.org/keywords/table","display_name":"Table (database)","score":0.6518660187721252},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6470308303833008},{"id":"https://openalex.org/keywords/weakness","display_name":"Weakness","score":0.5598379373550415},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.2571290135383606},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.2144697904586792},{"id":"https://openalex.org/keywords/medicine","display_name":"Medicine","score":0.08130869269371033}],"concepts":[{"id":"https://openalex.org/C2781235140","wikidata":"https://www.wikidata.org/wiki/Q275131","display_name":"Scratch","level":2,"score":0.6890825629234314},{"id":"https://openalex.org/C45235069","wikidata":"https://www.wikidata.org/wiki/Q278425","display_name":"Table (database)","level":2,"score":0.6518660187721252},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6470308303833008},{"id":"https://openalex.org/C2780247198","wikidata":"https://www.wikidata.org/wiki/Q633403","display_name":"Weakness","level":2,"score":0.5598379373550415},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.2571290135383606},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.2144697904586792},{"id":"https://openalex.org/C71924100","wikidata":"https://www.wikidata.org/wiki/Q11190","display_name":"Medicine","level":0,"score":0.08130869269371033},{"id":"https://openalex.org/C105702510","wikidata":"https://www.wikidata.org/wiki/Q514","display_name":"Anatomy","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.18653/v1/2025.findings-acl.381","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.findings-acl.381","pdf_url":"https://aclanthology.org/2025.findings-acl.381.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Findings of the Association for Computational Linguistics: ACL 2025","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.18653/v1/2025.findings-acl.381","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.findings-acl.381","pdf_url":"https://aclanthology.org/2025.findings-acl.381.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Findings of the Association for Computational Linguistics: ACL 2025","raw_type":"proceedings-article"},"sustainable_development_goals":[{"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4","score":0.41999998688697815}],"awards":[],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4412888395.pdf","grobid_xml":"https://content.openalex.org/works/W4412888395.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W2475116013","https://openalex.org/W2770018148","https://openalex.org/W2358308169","https://openalex.org/W2385135707","https://openalex.org/W2140315382","https://openalex.org/W2059109728","https://openalex.org/W322691623"],"abstract_inverted_index":{"Despite":[0],"the":[1,25,40,47,53,83,104,108,111,120,126,135,138,143],"commendable":[2],"progress":[3],"of":[4,29,46,55,103,110,137,146],"recent":[5],"LLM-based":[6],"data":[7,36,56,61,71,123,156,160,170],"synthesis":[8,72,161],"methods,":[9],"they":[10,20,38],"face":[11],"two":[12],"limitations":[13],"in":[14,42,59],"generating":[15],"table":[16,30,43,76],"instruction":[17,77],"tuning":[18],"data.First,":[19],"can":[21],"not":[22],"thoroughly":[23],"explore":[24],"vast":[26],"input":[27,105],"space":[28,106],"understanding":[31,44],"tasks,":[32],"leading":[33],"to":[34,81],"limited":[35],"diversity.Second,":[37],"ignore":[39],"weaknesses":[41],"ability":[45],"target":[48,127],"LLM":[49],"and":[50,69,91,97,157,169],"blindly":[51],"pursue":[52],"increase":[54],"quantity,":[57],"resulting":[58],"suboptimal":[60],"efficiency.In":[62],"this":[63],"paper,":[64],"we":[65,86],"introduce":[66],"a":[67],"progressive":[68],"weakness-guided":[70],"framework":[73],"tailored":[74],"for":[75,124],"tuning,":[78],"named":[79],"TableDreamer,":[80],"mitigate":[82],"above":[84],"issues.Specifically,":[85],"first":[87],"synthesize":[88],"diverse":[89],"tables":[90],"related":[92],"instructions":[93],"as":[94,119],"seed":[95],"data,":[96,115],"then":[98],"perform":[99],"an":[100],"iterative":[101],"exploration":[102],"under":[107],"guidance":[109],"newly":[112],"identified":[113],"weakness":[114],"which":[116,141,163],"eventually":[117],"serve":[118],"final":[121],"training":[122,166],"fine-tuning":[125],"LLM.Extensive":[128],"experiments":[129],"on":[130],"10":[131],"tabular":[132],"benchmarks":[133],"demonstrate":[134],"effectiveness":[136],"proposed":[139],"framework,":[140],"boosts":[142],"average":[144],"accuracy":[145],"Llama3.1-8B-instruct":[147],"by":[148],"11.62%":[149],"(49.07%":[150],"60.69%)":[151],"with":[152],"27K":[153],"GPT-4o":[154],"synthetic":[155],"outperforms":[158],"state-of-the-art":[159],"baselines":[162],"use":[164],"more":[165],"data.The":[167],"code":[168],"is":[171],"available":[172],"at":[173],"https://github.com/":[174],"SpursGoZmy/TableDreamer.":[175],"sample":[176]},"counts_by_year":[],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}