{"id":"https://openalex.org/W4402671077","doi":"https://doi.org/10.18653/v1/2024.findings-acl.16","title":"P-TA: Using Proximal Policy Optimization to Enhance Tabular Data Augmentation via Large Language Models","display_name":"P-TA: Using Proximal Policy Optimization to Enhance Tabular Data Augmentation via Large Language Models","publication_year":2024,"publication_date":"2024-01-01","ids":{"openalex":"https://openalex.org/W4402671077","doi":"https://doi.org/10.18653/v1/2024.findings-acl.16"},"language":"en","primary_location":{"id":"doi:10.18653/v1/2024.findings-acl.16","is_oa":true,"landing_page_url":"http://dx.doi.org/10.18653/v1/2024.findings-acl.16","pdf_url":"https://aclanthology.org/2024.findings-acl.16.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 2024","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://aclanthology.org/2024.findings-acl.16.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5111333851","display_name":"Shuo Yang","orcid":null},"institutions":[{"id":"https://openalex.org/I62916508","display_name":"Technical University of Munich","ror":"https://ror.org/02kkvpp62","country_code":"DE","type":"education","lineage":["https://openalex.org/I62916508"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Shuo Yang","raw_affiliation_strings":["Technical University of Munich , Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Technical University of Munich , Germany","institution_ids":["https://openalex.org/I62916508"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5099230566","display_name":"Chenchen Yuan","orcid":null},"institutions":[{"id":"https://openalex.org/I62916508","display_name":"Technical University of Munich","ror":"https://ror.org/02kkvpp62","country_code":"DE","type":"education","lineage":["https://openalex.org/I62916508"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Chenchen Yuan","raw_affiliation_strings":["Technical University of Munich , Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Technical University of Munich , Germany","institution_ids":["https://openalex.org/I62916508"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100624647","display_name":"Yao Rong","orcid":"https://orcid.org/0000-0002-6031-3741"},"institutions":[{"id":"https://openalex.org/I62916508","display_name":"Technical University of Munich","ror":"https://ror.org/02kkvpp62","country_code":"DE","type":"education","lineage":["https://openalex.org/I62916508"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Yao Rong","raw_affiliation_strings":["Technical University of Munich , Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Technical University of Munich , Germany","institution_ids":["https://openalex.org/I62916508"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5107544614","display_name":"Felix Steinbauer","orcid":null},"institutions":[{"id":"https://openalex.org/I62916508","display_name":"Technical University of Munich","ror":"https://ror.org/02kkvpp62","country_code":"DE","type":"education","lineage":["https://openalex.org/I62916508"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Felix Steinbauer","raw_affiliation_strings":["Technical University of Munich , Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Technical University of Munich , Germany","institution_ids":["https://openalex.org/I62916508"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5024434748","display_name":"Gjergji Kasneci","orcid":null},"institutions":[{"id":"https://openalex.org/I62916508","display_name":"Technical University of Munich","ror":"https://ror.org/02kkvpp62","country_code":"DE","type":"education","lineage":["https://openalex.org/I62916508"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Gjergji Kasneci","raw_affiliation_strings":["Technical University of Munich , Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Technical University of Munich , Germany","institution_ids":["https://openalex.org/I62916508"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.4329,"has_fulltext":true,"cited_by_count":1,"citation_normalized_percentile":{"value":0.67331966,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":95},"biblio":{"volume":null,"issue":null,"first_page":"248","last_page":"264"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11719","display_name":"Data Quality and Management","score":0.8026000261306763,"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"}},"topics":[{"id":"https://openalex.org/T11719","display_name":"Data Quality and Management","score":0.8026000261306763,"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"}},{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.7258999943733215,"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/computer-science","display_name":"Computer science","score":0.7057113647460938},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.3508361279964447}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7057113647460938},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.3508361279964447}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.18653/v1/2024.findings-acl.16","is_oa":true,"landing_page_url":"http://dx.doi.org/10.18653/v1/2024.findings-acl.16","pdf_url":"https://aclanthology.org/2024.findings-acl.16.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 2024","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.18653/v1/2024.findings-acl.16","is_oa":true,"landing_page_url":"http://dx.doi.org/10.18653/v1/2024.findings-acl.16","pdf_url":"https://aclanthology.org/2024.findings-acl.16.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 2024","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4402671077.pdf","grobid_xml":"https://content.openalex.org/works/W4402671077.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"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/W4395014643"],"abstract_inverted_index":{"A":[0],"multitude":[1],"of":[2,48,74,83,92,101,125,132,155],"industries":[3],"depend":[4],"on":[5,158],"accurate":[6],"and":[7,66],"reasonable":[8],"tabular":[9,19,126,140],"data":[10,20,68,161],"augmentation":[11],"for":[12,136],"their":[13],"business":[14],"processes.Contemporary":[15],"methodologies":[16],"in":[17,138,152],"generating":[18],"revolve":[21],"around":[22],"utilizing":[23],"Generative":[24],"Adversarial":[25],"Networks":[26],"(GAN)":[27],"or":[28],"fine-tuning":[29],"Large":[30],"Language":[31],"Models":[32],"(LLM).However,":[33],"GAN-based":[34],"approaches":[35],"are":[36],"documented":[37],"to":[38,45,60,71,115,120,147],"produce":[39],"samples":[40],"with":[41],"common-sense":[42],"errors":[43],"attributed":[44],"the":[46,51,62,72,81,90,99,122,130,153],"absence":[47,73],"external":[49],"knowledge.On":[50],"other":[52],"hand,":[53],"LLM-based":[54,84],"methods":[55],"exhibit":[56],"a":[57,77,95],"limited":[58],"capacity":[59],"capture":[61],"disparities":[63],"between":[64],"synthesized":[65],"actual":[67],"distribution":[69,124],"due":[70],"feedback":[75],"from":[76,94],"discriminator":[78],"during":[79],"training.Furthermore,":[80],"decoding":[82],"generation":[85],"introduces":[86],"gradient":[87],"breakpoints,":[88],"impeding":[89],"backpropagation":[91],"loss":[93],"discriminator,":[96],"thereby":[97],"complicating":[98],"integration":[100],"these":[102],"two":[103],"approaches.To":[104],"solve":[105],"this":[106],"challenge,":[107],"we":[108],"propose":[109],"using":[110],"proximal":[111],"policy":[112],"optimization":[113],"(PPO)":[114],"apply":[116],"GANs,":[117],"guiding":[118],"LLMs":[119,133],"enhance":[121],"probability":[123],"features.This":[127],"approach":[128],"enables":[129],"utilization":[131],"as":[134],"generators":[135],"GANs":[137],"synthesizing":[139],"data.Our":[141],"experiments":[142],"demonstrate":[143],"that":[144],"PPO":[145],"leads":[146],"an":[148],"approximately":[149],"4%":[150],"improvement":[151],"accuracy":[154],"models":[156],"trained":[157],"synthetically":[159],"generated":[160],"over":[162],"state-of-the-art":[163],"across":[164],"three":[165],"real-world":[166],"datasets.":[167]},"counts_by_year":[{"year":2025,"cited_by_count":1}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}