{"id":"https://openalex.org/W7140127683","doi":"https://doi.org/10.18653/v1/2026.eacl-long.28","title":"PromptFE: Automated Feature Engineering by Prompting","display_name":"PromptFE: Automated Feature Engineering by Prompting","publication_year":2026,"publication_date":"2026-01-01","ids":{"openalex":"https://openalex.org/W7140127683","doi":"https://doi.org/10.18653/v1/2026.eacl-long.28"},"language":null,"primary_location":{"id":"doi:10.18653/v1/2026.eacl-long.28","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.eacl-long.28","pdf_url":"https://aclanthology.org/2026.eacl-long.28.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":"Proceedings of the 19th Conference of the European Chapter of the Association for Computational Linguistics (Volume 1: Long Papers)","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://aclanthology.org/2026.eacl-long.28.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5130365953","display_name":"Yufeng Zou","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yufeng Zou","raw_affiliation_strings":["Northwestern University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Northwestern University","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5060826513","display_name":"Jean Utke","orcid":"https://orcid.org/0000-0002-3377-1990"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jean Utke","raw_affiliation_strings":["Northwestern University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Northwestern University","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5013049879","display_name":"Diego Klabjan","orcid":"https://orcid.org/0000-0003-4213-9281"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Diego Klabjan","raw_affiliation_strings":["Northwestern University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Northwestern University","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5130394196","display_name":"Han Liu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Han Liu","raw_affiliation_strings":["Northwestern University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Northwestern University","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":4,"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":0.39934073,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"653","last_page":"681"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12535","display_name":"Machine Learning and Data Classification","score":0.11540000140666962,"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/T12535","display_name":"Machine Learning and Data Classification","score":0.11540000140666962,"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":0.04740000143647194,"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/T10538","display_name":"Data Mining Algorithms and Applications","score":0.040300000458955765,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"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/feature","display_name":"Feature (linguistics)","score":0.5152999758720398},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3075999915599823},{"id":"https://openalex.org/keywords/automation","display_name":"Automation","score":0.29660001397132874},{"id":"https://openalex.org/keywords/matching","display_name":"Matching (statistics)","score":0.26190000772476196},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.24629999697208405}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5896000266075134},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5712000131607056},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.5152999758720398},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.4415999948978424},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3075999915599823},{"id":"https://openalex.org/C115901376","wikidata":"https://www.wikidata.org/wiki/Q184199","display_name":"Automation","level":2,"score":0.29660001397132874},{"id":"https://openalex.org/C165064840","wikidata":"https://www.wikidata.org/wiki/Q1321061","display_name":"Matching (statistics)","level":2,"score":0.26190000772476196},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.24629999697208405},{"id":"https://openalex.org/C9652623","wikidata":"https://www.wikidata.org/wiki/Q190109","display_name":"Field (mathematics)","level":2,"score":0.23929999768733978},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.23489999771118164}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.18653/v1/2026.eacl-long.28","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.eacl-long.28","pdf_url":"https://aclanthology.org/2026.eacl-long.28.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":"Proceedings of the 19th Conference of the European Chapter of the Association for Computational Linguistics (Volume 1: Long Papers)","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.18653/v1/2026.eacl-long.28","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.eacl-long.28","pdf_url":"https://aclanthology.org/2026.eacl-long.28.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":"Proceedings of the 19th Conference of the European Chapter of the Association for Computational Linguistics (Volume 1: Long Papers)","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7140127683.pdf","grobid_xml":"https://content.openalex.org/works/W7140127683.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Automated":[0],"feature":[1,12,23,75,106],"engineering":[2,24],"(AutoFE)":[3],"liberates":[4],"data":[5],"scientists":[6],"from":[7],"the":[8,64,71,83,93,104],"burden":[9],"of":[10,16,66,86,95],"manual":[11],"construction.The":[13],"semantic":[14,57,97],"information":[15,21,98],"datasets":[17,82],"contains":[18],"rich":[19],"context":[20],"for":[22],"but":[25],"has":[26],"been":[27],"underutilized":[28],"in":[29,50,69],"many":[30],"existing":[31],"AutoFE":[32,38,90],"works.We":[33],"present":[34],"PromptFE,":[35],"a":[36,51],"novel":[37],"framework":[39],"that":[40],"leverages":[41],"large":[42],"language":[43],"models":[44],"(LLMs)":[45],"to":[46],"automatically":[47],"construct":[48],"features":[49,68],"compact":[52],"string":[53],"format":[54],"and":[55,99],"generate":[56],"explanations":[58],"based":[59],"on":[60,80,103],"dataset":[61,96],"descriptions.By":[62],"learning":[63],"performance":[65,85],"constructed":[67],"context,":[70],"LLM":[72],"iteratively":[73],"improves":[74],"construction.We":[76],"demonstrate":[77],"through":[78],"experiments":[79],"real-world":[81],"superior":[84],"PromptFE":[87],"over":[88],"state-ofthe-art":[89],"methods.We":[91],"verify":[92],"impact":[94],"provide":[100],"comprehensive":[101],"study":[102],"LLM-based":[105],"construction":[107],"process.":[108]},"counts_by_year":[],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2026-03-24T00:00:00"}