{"id":"https://openalex.org/W7204818503","doi":"https://doi.org/10.18653/2026.emnlp-main.1476","title":"SymboLLM-FE: LLM-Accelerated Symbolic Regression for Automated Feature Engineering on Tabular Data","display_name":"SymboLLM-FE: LLM-Accelerated Symbolic Regression for Automated Feature Engineering on Tabular Data","publication_year":2026,"publication_date":"2026-01-01","ids":{"openalex":"https://openalex.org/W7204818503","doi":"https://doi.org/10.18653/2026.emnlp-main.1476"},"language":"en","primary_location":{"id":"doi:10.18653/2026.emnlp-main.1476","doi":"https://doi.org/10.18653/2026.emnlp-main.1476","is_oa":true,"landing_page_url":"https://doi.org/10.18653/2026.emnlp-main.1476","pdf_url":"https://aclanthology.org/2026.emnlp-main.1476.pdf","source":{"id":"https://openalex.org/S4363608991","display_name":"Conference on Empirical Methods in Natural Language Processing (EMNLP)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2026 Conference on Empirical Methods in Natural Language Processing","raw_type":"proceedings-article"},"volume":null,"type":"conference-paper","is_traditional":true,"indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"bronze","oa_url":"https://aclanthology.org/2026.emnlp-main.1476.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5120417002","display_name":"Zi-Jian Cheng","orcid":"https://orcid.org/0009-0004-3123-8262","observed_orcids":["https://orcid.org/0009-0004-3123-8262"]},"institutions":[{"id":"https://openalex.org/I881766915","display_name":"Nanjing University","ror":"https://ror.org/01rxvg760","country_code":"CN","type":"education","lineage":["https://openalex.org/I881766915"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zi-Jian Cheng","raw_affiliation_strings":["National Key Laboratory for Novel Software Technology , Nanjing University","School of Intelligence Science and Technology , Nanjing University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National Key Laboratory for Novel Software Technology , Nanjing University","institution_ids":["https://openalex.org/I881766915"]},{"raw_affiliation_string":"School of Intelligence Science and Technology , Nanjing University","institution_ids":["https://openalex.org/I881766915"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5130716684","display_name":"Zi-Yi Jia","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I881766915","display_name":"Nanjing University","ror":"https://ror.org/01rxvg760","country_code":"CN","type":"education","lineage":["https://openalex.org/I881766915"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ziyi Jia","raw_affiliation_strings":["National Key Laboratory for Novel Software Technology , Nanjing University","School of Intelligence Science and Technology , Nanjing University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National Key Laboratory for Novel Software Technology , Nanjing University","institution_ids":["https://openalex.org/I881766915"]},{"raw_affiliation_string":"School of Intelligence Science and Technology , Nanjing University","institution_ids":["https://openalex.org/I881766915"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5136049471","display_name":"Zhi Zhou","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I881766915","display_name":"Nanjing University","ror":"https://ror.org/01rxvg760","country_code":"CN","type":"education","lineage":["https://openalex.org/I881766915"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhi Zhou","raw_affiliation_strings":["National Key Laboratory for Novel Software Technology , Nanjing University","School of Artificial Intelligence , Nanjing University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National Key Laboratory for Novel Software Technology , Nanjing University","institution_ids":["https://openalex.org/I881766915"]},{"raw_affiliation_string":"School of Artificial Intelligence , Nanjing University","institution_ids":["https://openalex.org/I881766915"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5126365288","display_name":"Yu-Feng Li","orcid":"https://orcid.org/0000-0002-2220-5248","observed_orcids":["https://orcid.org/0000-0002-2220-5248"]},"institutions":[{"id":"https://openalex.org/I881766915","display_name":"Nanjing University","ror":"https://ror.org/01rxvg760","country_code":"CN","type":"education","lineage":["https://openalex.org/I881766915"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yu-Feng Li","raw_affiliation_strings":["National Key Laboratory for Novel Software Technology , Nanjing University","School of Artificial Intelligence , Nanjing University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National Key Laboratory for Novel Software Technology , Nanjing University","institution_ids":["https://openalex.org/I881766915"]},{"raw_affiliation_string":"School of Artificial Intelligence , Nanjing University","institution_ids":["https://openalex.org/I881766915"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5130197296","display_name":"Lan-Zhe Guo","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I881766915","display_name":"Nanjing University","ror":"https://ror.org/01rxvg760","country_code":"CN","type":"education","lineage":["https://openalex.org/I881766915"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Lan-Zhe Guo","raw_affiliation_strings":["National Key Laboratory for Novel Software Technology , Nanjing University","School of Intelligence Science and Technology , Nanjing University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National Key Laboratory for Novel Software Technology , Nanjing University","institution_ids":["https://openalex.org/I881766915"]},{"raw_affiliation_string":"School of Intelligence Science and Technology , Nanjing University","institution_ids":["https://openalex.org/I881766915"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I881766915"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.56757561,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"33744","last_page":"33770"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11975","display_name":"Evolutionary Algorithms and Applications","score":0.4961000084877014,"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/T11975","display_name":"Evolutionary Algorithms and Applications","score":0.4961000084877014,"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/T12535","display_name":"Machine Learning and Data Classification","score":0.23659999668598175,"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":0.06400000303983688,"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/automated-feature-engineering","display_name":"automated feature engineering","score":0.9599999785423279},{"id":"https://openalex.org/keywords/symbolic-regression","display_name":"symbolic regression","score":0.9390000104904175},{"id":"https://openalex.org/keywords/large-language-models","display_name":"large language models","score":0.9419999718666077},{"id":"https://openalex.org/keywords/tabular-data","display_name":"tabular data","score":0.9990000128746033},{"id":"https://openalex.org/keywords/feature-interpretability","display_name":"feature interpretability","score":0.8740000128746033},{"id":"https://openalex.org/keywords/feature-construction","display_name":"feature construction","score":0.5400000214576721},{"id":"https://openalex.org/keywords/feature-selection","display_name":"feature selection","score":0.8759999871253967},{"id":"https://openalex.org/keywords/hallucination-risk","display_name":"hallucination risk","score":0.5339999794960022}],"concepts":[{"id":"https://openalex.org/C2781067378","wikidata":"https://www.wikidata.org/wiki/Q17027399","display_name":"Interpretability","level":2,"score":0.9380999803543091},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7698000073432922},{"id":"https://openalex.org/C97931131","wikidata":"https://www.wikidata.org/wiki/Q5282087","display_name":"Discriminative model","level":2,"score":0.6909000277519226},{"id":"https://openalex.org/C2778827112","wikidata":"https://www.wikidata.org/wiki/Q22245680","display_name":"Feature engineering","level":3,"score":0.6757000088691711},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.6672000288963318},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6104000210762024},{"id":"https://openalex.org/C2776400721","wikidata":"https://www.wikidata.org/wiki/Q18171762","display_name":"Symbolic regression","level":3,"score":0.5900999903678894},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5740000009536743},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.42829999327659607},{"id":"https://openalex.org/C114289077","wikidata":"https://www.wikidata.org/wiki/Q3284399","display_name":"Statistical model","level":2,"score":0.4027000069618225},{"id":"https://openalex.org/C101814296","wikidata":"https://www.wikidata.org/wiki/Q5439685","display_name":"Feature model","level":3,"score":0.391400009393692},{"id":"https://openalex.org/C195818886","wikidata":"https://www.wikidata.org/wiki/Q5421724","display_name":"Expressive power","level":2,"score":0.37439998984336853},{"id":"https://openalex.org/C158154518","wikidata":"https://www.wikidata.org/wiki/Q7310970","display_name":"Relevance (law)","level":2,"score":0.3718999922275543},{"id":"https://openalex.org/C67186912","wikidata":"https://www.wikidata.org/wiki/Q367664","display_name":"Data modeling","level":2,"score":0.37139999866485596},{"id":"https://openalex.org/C12267149","wikidata":"https://www.wikidata.org/wiki/Q282453","display_name":"Support vector machine","level":2,"score":0.36579999327659607},{"id":"https://openalex.org/C75684735","wikidata":"https://www.wikidata.org/wiki/Q858810","display_name":"Big data","level":2,"score":0.36410000920295715},{"id":"https://openalex.org/C148483581","wikidata":"https://www.wikidata.org/wiki/Q446488","display_name":"Feature selection","level":2,"score":0.3125999867916107},{"id":"https://openalex.org/C2780980858","wikidata":"https://www.wikidata.org/wiki/Q110022","display_name":"Dual (grammatical number)","level":2,"score":0.3084000051021576},{"id":"https://openalex.org/C83546350","wikidata":"https://www.wikidata.org/wiki/Q1139051","display_name":"Regression","level":2,"score":0.3070000112056732},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.29600000381469727},{"id":"https://openalex.org/C49937458","wikidata":"https://www.wikidata.org/wiki/Q2599292","display_name":"Probabilistic logic","level":2,"score":0.289900004863739},{"id":"https://openalex.org/C83665646","wikidata":"https://www.wikidata.org/wiki/Q42139305","display_name":"Feature vector","level":2,"score":0.2842999994754791},{"id":"https://openalex.org/C152877465","wikidata":"https://www.wikidata.org/wiki/Q208042","display_name":"Regression analysis","level":2,"score":0.27720001339912415},{"id":"https://openalex.org/C59404180","wikidata":"https://www.wikidata.org/wiki/Q17013334","display_name":"Feature learning","level":2,"score":0.2766999900341034},{"id":"https://openalex.org/C2776145971","wikidata":"https://www.wikidata.org/wiki/Q30673951","display_name":"Labeled data","level":2,"score":0.27149999141693115},{"id":"https://openalex.org/C163258240","wikidata":"https://www.wikidata.org/wiki/Q25342","display_name":"Power (physics)","level":2,"score":0.2705000042915344},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.26460000872612},{"id":"https://openalex.org/C77618280","wikidata":"https://www.wikidata.org/wiki/Q1155772","display_name":"Scheme (mathematics)","level":2,"score":0.26179999113082886},{"id":"https://openalex.org/C120936955","wikidata":"https://www.wikidata.org/wiki/Q2155640","display_name":"Empirical research","level":2,"score":0.2581999897956848}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.18653/2026.emnlp-main.1476","doi":"https://doi.org/10.18653/2026.emnlp-main.1476","is_oa":true,"landing_page_url":"https://doi.org/10.18653/2026.emnlp-main.1476","pdf_url":"https://aclanthology.org/2026.emnlp-main.1476.pdf","source":{"id":"https://openalex.org/S4363608991","display_name":"Conference on Empirical Methods in Natural Language Processing (EMNLP)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2026 Conference on Empirical Methods in Natural Language Processing","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2608.28408","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2608.28408","pdf_url":"https://arxiv.org/pdf/2608.28408","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2608.28408","doi":"https://doi.org/10.48550/arxiv.2608.28408","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2608.28408","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"doi:10.18653/2026.emnlp-main.1476","doi":"https://doi.org/10.18653/2026.emnlp-main.1476","is_oa":true,"landing_page_url":"https://doi.org/10.18653/2026.emnlp-main.1476","pdf_url":"https://aclanthology.org/2026.emnlp-main.1476.pdf","source":{"id":"https://openalex.org/S4363608991","display_name":"Conference on Empirical Methods in Natural Language Processing (EMNLP)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2026 Conference on Empirical Methods in Natural Language Processing","raw_type":"proceedings-article"},"sustainable_development_goals":[],"study_designs":[],"awards":[{"id":"https://openalex.org/G4702392992","display_name":null,"funder_award_id":"B26023","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G6712651544","display_name":null,"funder_award_id":"B26023","funder_id":"https://openalex.org/F4320336698","funder_display_name":"Overseas Expertise Introduction Center for Discipline Innovation of Food Nutrition and Human Health (111 Center)"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320336698","display_name":"Overseas Expertise Introduction Center for Discipline Innovation of Food Nutrition and Human Health (111 Center)","ror":null}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7204818503.pdf","grobid_xml":"https://content.openalex.org/works/W7204818503.grobid-xml"},"referenced_works_count":17,"referenced_works":["https://openalex.org/W2971569798","https://openalex.org/W3015984827","https://openalex.org/W3171590774","https://openalex.org/W3174986053","https://openalex.org/W3205068155","https://openalex.org/W4387432132","https://openalex.org/W4394866599","https://openalex.org/W4400375614","https://openalex.org/W4408013490","https://openalex.org/W4413361023","https://openalex.org/W4414992338","https://openalex.org/W4416234289","https://openalex.org/W6948122304","https://openalex.org/W7130554117","https://openalex.org/W7140428524","https://openalex.org/W7160931912","https://openalex.org/W7196926871"],"related_works":["https://openalex.org/W7204863770","https://openalex.org/W6948122304","https://openalex.org/W7160706898","https://openalex.org/W7196933902","https://openalex.org/W4411120509","https://openalex.org/W4409657365","https://openalex.org/W4414989093","https://openalex.org/W7126214529","https://openalex.org/W7133188930","https://openalex.org/W7168176269"],"abstract_inverted_index":{"Tabular":[0],"data,":[1],"as":[2],"a":[3,160],"core":[4],"data":[5],"format":[6],"in":[7,65],"machine":[8],"learning,":[9],"often":[10,44],"lacks":[11],"the":[12,110,149],"discriminative":[13],"power":[14],"needed":[15],"for":[16,95],"high-performance":[17],"modeling":[18],"due":[19],"to":[20,70,74,99,129],"insufficient":[21],"feature":[22,31,96],"informativeness.Automated":[23],"Feature":[24],"Engineering":[25],"(AutoFE)":[26],"overcomes":[27],"this":[28,87],"by":[29,80,123,158],"automating":[30],"generation":[32],"and":[33,39,85,137,155,166],"selection,":[34],"ensuring":[35],"both":[36],"model":[37,77,118],"performance":[38],"operational":[40],"efficiency.However,":[41],"traditional":[42],"AutoFE":[43,62],"yield":[45],"features":[46,73],"with":[47,93,109,125],"poor":[48,153],"interpretability":[49,154],"because":[50],"they":[51],"rely":[52],"on":[53,133],"blind":[54],"mathematical":[55],"transformations,":[56],"while":[57],"large":[58],"language":[59],"models":[60],"(LLM)-based":[61],"faces":[63],"challenges":[64,151],"requiring":[66],"costly":[67],"multi-round":[68],"iterations":[69,157],"generate":[71],"high-utility":[72],"effectively":[75],"enhance":[76,117],"performance,":[78,119],"compounded":[79],"inherent":[81],"risks":[82],"of":[83,152],"bias":[84],"hallucination.In":[86],"paper,":[88],"we":[89],"combine":[90],"symbolic":[91,113],"regression":[92],"LLMs":[94,124],"engineering":[97],"(SymboLLM-FE)":[98],"solve":[100],"these":[101],"challenges.We":[102],"extract":[103],"mathematically":[104],"expressive":[105],"formulas":[106],"strongly":[107],"correlated":[108],"target":[111],"via":[112],"regression,":[114],"which":[115],"can":[116],"then":[120],"refine":[121],"them":[122],"rich":[126],"prior":[127],"knowledge":[128],"ensure":[130],"interpretability.Empirical":[131],"results":[132],"six":[134],"real-world":[135],"datasets":[136],"four":[138],"Kaggle":[139],"competitions":[140],"demonstrate":[141],"that":[142],"SymboLLM-FE":[143],"outperforms":[144],"existing":[145],"AutoFE.SymboLLM-FE":[146],"also":[147],"addresses":[148],"dual":[150],"numerous":[156],"employing":[159],"statistical":[161],"prior-grounded":[162],"LLM":[163,168],"refinement":[164],"mechanism":[165],"single-digit":[167],"calls.":[169]},"counts_by_year":[],"updated_date":"2026-11-07T11:25:07.637180","created_date":"2026-09-01T00:00:00"}