{"id":"https://openalex.org/W4406461297","doi":"https://doi.org/10.1109/bigdata62323.2024.10825204","title":"TIFG: Text-Informed Feature Generation with Large Language Models","display_name":"TIFG: Text-Informed Feature Generation with Large Language Models","publication_year":2024,"publication_date":"2024-12-15","ids":{"openalex":"https://openalex.org/W4406461297","doi":"https://doi.org/10.1109/bigdata62323.2024.10825204"},"language":"en","primary_location":{"id":"doi:10.1109/bigdata62323.2024.10825204","is_oa":false,"landing_page_url":"https://doi.org/10.1109/bigdata62323.2024.10825204","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE International Conference on Big Data (BigData)","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/A5100315423","display_name":"Xinhao Zhang","orcid":"https://orcid.org/0009-0001-1586-5571"},"institutions":[{"id":"https://openalex.org/I126345244","display_name":"Portland State University","ror":"https://ror.org/00yn2fy02","country_code":"US","type":"education","lineage":["https://openalex.org/I126345244"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Xinhao Zhang","raw_affiliation_strings":["Portland State University,Department of Computer Science,Portland,USA"],"affiliations":[{"raw_affiliation_string":"Portland State University,Department of Computer Science,Portland,USA","institution_ids":["https://openalex.org/I126345244"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100786547","display_name":"Kunpeng Liu","orcid":"https://orcid.org/0000-0002-6053-5977"},"institutions":[{"id":"https://openalex.org/I126345244","display_name":"Portland State University","ror":"https://ror.org/00yn2fy02","country_code":"US","type":"education","lineage":["https://openalex.org/I126345244"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Kunpeng Liu","raw_affiliation_strings":["Portland State University,Department of Computer Science,Portland,USA"],"affiliations":[{"raw_affiliation_string":"Portland State University,Department of Computer Science,Portland,USA","institution_ids":["https://openalex.org/I126345244"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5100315423"],"corresponding_institution_ids":["https://openalex.org/I126345244"],"apc_list":null,"apc_paid":null,"fwci":1.4464,"has_fulltext":false,"cited_by_count":4,"citation_normalized_percentile":{"value":0.8592447,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"8256","last_page":"8258"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.9997000098228455,"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":0.9997000098228455,"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":0.9976000189781189,"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/T11550","display_name":"Text and Document Classification Technologies","score":0.996399998664856,"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":0.7876834869384766},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.6369467973709106},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.5879301428794861},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5420502424240112},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.28119081258773804}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7876834869384766},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.6369467973709106},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.5879301428794861},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5420502424240112},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.28119081258773804},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/bigdata62323.2024.10825204","is_oa":false,"landing_page_url":"https://doi.org/10.1109/bigdata62323.2024.10825204","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE International Conference on Big Data (BigData)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":11,"referenced_works":["https://openalex.org/W2604662567","https://openalex.org/W2759903677","https://openalex.org/W2783320270","https://openalex.org/W2898085636","https://openalex.org/W3101704389","https://openalex.org/W3176309799","https://openalex.org/W4281638598","https://openalex.org/W4397028113","https://openalex.org/W4399453708","https://openalex.org/W6866362536","https://openalex.org/W6869394356"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W2390279801","https://openalex.org/W4391913857","https://openalex.org/W2358668433","https://openalex.org/W4396701345","https://openalex.org/W2376932109","https://openalex.org/W2001405890","https://openalex.org/W3204019825"],"abstract_inverted_index":{"Textual":[0],"information":[1,27,70],"of":[2,5,139],"data":[3,9,21,44,127],"is":[4,156],"vital":[6],"importance":[7],"for":[8],"mining":[10],"and":[11,23,38,103,129,152,155],"feature":[12,63,101,106,121],"engineering.":[13],"However,":[14],"existing":[15,160],"methods":[16],"focus":[17],"on":[18,41],"learning":[19],"the":[20,25,30,42,48,68,91,100,110,120],"structures":[22],"overlook":[24],"textual":[26,69],"along":[28],"with":[29,82],"data.":[31],"Consequently,":[32],"they":[33],"waste":[34],"this":[35,51,89],"valuable":[36],"resource":[37],"miss":[39],"out":[40],"deeper":[43],"relationships":[45],"embedded":[46],"within":[47,79],"texts.":[49],"In":[50,88],"paper,":[52],"we":[53],"introduce":[54],"Text-Informed":[55],"Feature":[56],"Generation":[57,85],"(TIFG),":[58],"a":[59],"novel":[60],"LLM-based":[61],"text-informed":[62],"generation":[64,122],"framework.":[65],"TIFG":[66,92,111],"utilizes":[67],"to":[71,98,112,125,159],"generate":[72,94,150],"features":[73,78,97],"by":[74],"retrieving":[75],"possible":[76],"relevant":[77],"external":[80],"knowledge":[81],"Retrieval":[83],"Augmented":[84],"(RAG)":[86],"technology.":[87],"approach,":[90],"can":[93,149],"new":[95,126],"explainable":[96],"enrich":[99],"space":[102],"further":[104],"mine":[105],"relationships.":[107],"We":[108],"design":[109],"be":[113],"an":[114],"automated":[115],"framework":[116],"that":[117,146],"continuously":[118],"optimizes":[119],"process,":[123],"adapts":[124],"inputs,":[128],"improves":[130],"downstream":[131,143],"task":[132],"performance":[133],"over":[134],"iterations.":[135],"A":[136],"broad":[137],"range":[138],"experiments":[140],"in":[141],"various":[142],"tasks":[144],"showcases":[145],"our":[147],"approach":[148],"high-quality":[151],"meaningful":[153],"features,":[154],"significantly":[157],"superior":[158],"methods.":[161]},"counts_by_year":[{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":1}],"updated_date":"2026-03-12T08:34:05.389933","created_date":"2025-10-10T00:00:00"}