{"id":"https://openalex.org/W4416033926","doi":"https://doi.org/10.18653/v1/2025.findings-emnlp.1055","title":"Attributes as Textual Genes: Leveraging LLMs as Genetic Algorithm Simulators for Conditional Synthetic Data Generation","display_name":"Attributes as Textual Genes: Leveraging LLMs as Genetic Algorithm Simulators for Conditional Synthetic Data Generation","publication_year":2025,"publication_date":"2025-01-01","ids":{"openalex":"https://openalex.org/W4416033926","doi":"https://doi.org/10.18653/v1/2025.findings-emnlp.1055"},"language":null,"primary_location":{"id":"doi:10.18653/v1/2025.findings-emnlp.1055","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.findings-emnlp.1055","pdf_url":"https://aclanthology.org/2025.findings-emnlp.1055.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: EMNLP 2025","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://aclanthology.org/2025.findings-emnlp.1055.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5013948381","display_name":"Guangzeng Han","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Guangzeng Han","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5063635932","display_name":"Weisi Liu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Weisi Liu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5027237221","display_name":"Xiaolei Huang","orcid":"https://orcid.org/0000-0003-0478-8715"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xiaolei Huang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.6796,"has_fulltext":true,"cited_by_count":1,"citation_normalized_percentile":{"value":0.89009276,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":95,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"19367","last_page":"19389"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.2125999927520752,"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":0.2125999927520752,"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":0.11509999632835388,"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/T12072","display_name":"Machine Learning and Algorithms","score":0.10130000114440918,"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/genetic-algorithm","display_name":"Genetic algorithm","score":0.5325000286102295},{"id":"https://openalex.org/keywords/synthetic-data","display_name":"Synthetic data","score":0.48010000586509705},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.32510000467300415},{"id":"https://openalex.org/keywords/genetic-data","display_name":"Genetic data","score":0.3027999997138977},{"id":"https://openalex.org/keywords/real-world-data","display_name":"Real world data","score":0.26030001044273376}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6308000087738037},{"id":"https://openalex.org/C8880873","wikidata":"https://www.wikidata.org/wiki/Q187787","display_name":"Genetic algorithm","level":2,"score":0.5325000286102295},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4805999994277954},{"id":"https://openalex.org/C160920958","wikidata":"https://www.wikidata.org/wiki/Q7662746","display_name":"Synthetic data","level":2,"score":0.48010000586509705},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.4027000069618225},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3763999938964844},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.3264000117778778},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.32510000467300415},{"id":"https://openalex.org/C2993807623","wikidata":"https://www.wikidata.org/wiki/Q7020","display_name":"Genetic data","level":3,"score":0.3027999997138977},{"id":"https://openalex.org/C3020493868","wikidata":"https://www.wikidata.org/wiki/Q55631277","display_name":"Real world data","level":2,"score":0.26030001044273376},{"id":"https://openalex.org/C2781170535","wikidata":"https://www.wikidata.org/wiki/Q30587856","display_name":"Noisy data","level":2,"score":0.2565999925136566},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.25279998779296875}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.18653/v1/2025.findings-emnlp.1055","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.findings-emnlp.1055","pdf_url":"https://aclanthology.org/2025.findings-emnlp.1055.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: EMNLP 2025","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.18653/v1/2025.findings-emnlp.1055","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.findings-emnlp.1055","pdf_url":"https://aclanthology.org/2025.findings-emnlp.1055.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: EMNLP 2025","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G5912204943","display_name":"Equipment: MRI: Track 2 Acquisition of a HPC Cluster for Fostering Interdisciplinary Collaboration on AI-driven and Data-intensive Research and Education in West Tennessee","funder_award_id":"2318210","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G6216730209","display_name":"CRII: III: Metadata-guided Imbalance-Modeling for Robust Computational Healthcare","funder_award_id":"2245920","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G8391963529","display_name":null,"funder_award_id":"IIS-2245920","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"}],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"},{"id":"https://openalex.org/F4320312842","display_name":"University of Memphis","ror":null}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4416033926.pdf","grobid_xml":"https://content.openalex.org/works/W4416033926.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Large":[0],"Language":[1],"Models":[2],"(LLMs)":[3],"excel":[4],"at":[5],"generating":[6],"synthetic":[7,33,67,123,151],"data,":[8],"but":[9,106],"ensuring":[10],"its":[11],"quality":[12,58],"and":[13,44,51,59,116],"diversity":[14,60],"remains":[15],"challenging.We":[16],"propose":[17],"Genetic":[18,98,142],"Prompt":[19,99,143],"1":[20],",":[21],"a":[22,154],"novel":[23,63],"framework":[24],"that":[25,83,120,141],"combines":[26],"genetic":[27,54],"algorithms":[28],"with":[29,125],"LLMs":[30],"to":[31,48,70],"augment":[32],"data":[34,57,124,152],"generation.Our":[35],"approach":[36],"treats":[37],"semantic":[38],"text":[39],"attributes":[40],"as":[41],"gene":[42],"sequences":[43],"leverages":[45],"the":[46,85,126],"LLM":[47],"simulate":[49],"crossover":[50],"mutation":[52],"operations.This":[53],"process":[55],"enhances":[56],"by":[61],"creating":[62],"attribute":[64],"combinations,":[65],"yielding":[66],"distributions":[68],"closer":[69],"real-world":[71],"data.To":[72],"optimize":[73],"parent":[74],"selection,":[75],"we":[76,118],"also":[77,107],"integrate":[78],"an":[79,145],"active":[80],"learning":[81],"scheme":[82],"expands":[84],"offspring":[86],"search":[87],"space.Our":[88],"experiments":[89],"on":[90],"multiple":[91],"NLP":[92,158],"tasks":[93],"reveal":[94],"several":[95],"key":[96],"findings:":[97],"not":[100],"only":[101],"significantly":[102,130],"outperforms":[103],"stateof-the-art":[104],"baselines":[105],"shows":[108],"robust":[109],"performance":[110],"across":[111],"various":[112],"generator":[113],"model":[114,133],"sizes":[115],"scales.Moreover,":[117],"demonstrate":[119],"fusing":[121],"our":[122],"original":[127],"training":[128],"set":[129],"boosts":[131],"downstream":[132],"performance,":[134],"particularly":[135],"for":[136,148,153],"class-imbalanced":[137],"scenarios.Our":[138],"findings":[139],"validate":[140],"is":[144],"effective":[146],"method":[147],"producing":[149],"high-quality":[150],"wide":[155],"range":[156],"of":[157],"applications.":[159]},"counts_by_year":[{"year":2026,"cited_by_count":1}],"updated_date":"2026-06-22T08:00:12.763002","created_date":"2025-11-08T00:00:00"}