{"id":"https://openalex.org/W4403582570","doi":"https://doi.org/10.1145/3627673.3679153","title":"ELF-Gym: Evaluating Large Language Models Generated Features for Tabular Prediction","display_name":"ELF-Gym: Evaluating Large Language Models Generated Features for Tabular Prediction","publication_year":2024,"publication_date":"2024-10-20","ids":{"openalex":"https://openalex.org/W4403582570","doi":"https://doi.org/10.1145/3627673.3679153"},"language":"en","primary_location":{"id":"doi:10.1145/3627673.3679153","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3627673.3679153","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 33rd ACM International Conference on Information and Knowledge Management","raw_type":"proceedings-article"},"type":"conference-paper","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/A5083294683","display_name":"Yanlin Zhang","orcid":"https://orcid.org/0009-0001-0104-238X"},"institutions":[{"id":"https://openalex.org/I24943067","display_name":"Fudan University","ror":"https://ror.org/013q1eq08","country_code":"CN","type":"education","lineage":["https://openalex.org/I24943067"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yanlin Zhang","raw_affiliation_strings":["Fudan University, Shanghai, China"],"raw_orcid":"https://orcid.org/0009-0001-0104-238X","affiliations":[{"raw_affiliation_string":"Fudan University, Shanghai, China","institution_ids":["https://openalex.org/I24943067"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101734871","display_name":"Ning Li","orcid":"https://orcid.org/0009-0000-5941-6412"},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ning Li","raw_affiliation_strings":["Shanghai Jiao Tong University, Shanghai, China"],"raw_orcid":"https://orcid.org/0009-0000-5941-6412","affiliations":[{"raw_affiliation_string":"Shanghai Jiao Tong University, Shanghai, China","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5031121810","display_name":"Quan Gan","orcid":"https://orcid.org/0009-0002-0986-457X"},"institutions":[{"id":"https://openalex.org/I4391012619","display_name":"Shanghai Artificial Intelligence Laboratory","ror":"https://ror.org/03wkvpx79","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4391012619"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Quan Gan","raw_affiliation_strings":["Amazon Shanghai AI Lab, Shanghai, China"],"raw_orcid":"https://orcid.org/0009-0002-0986-457X","affiliations":[{"raw_affiliation_string":"Amazon Shanghai AI Lab, Shanghai, China","institution_ids":["https://openalex.org/I4391012619"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5090720315","display_name":"Weinan Zhang","orcid":"https://orcid.org/0000-0002-0127-2425"},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Weinan Zhang","raw_affiliation_strings":["Shanghai Jiao Tong University, Shanghai, China"],"raw_orcid":"https://orcid.org/0000-0002-0127-2425","affiliations":[{"raw_affiliation_string":"Shanghai Jiao Tong University, Shanghai, China","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5085016531","display_name":"David Wipf","orcid":"https://orcid.org/0000-0002-2768-4540"},"institutions":[{"id":"https://openalex.org/I4391012619","display_name":"Shanghai Artificial Intelligence Laboratory","ror":"https://ror.org/03wkvpx79","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4391012619"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"David Wipf","raw_affiliation_strings":["Amazon Shanghai AI Lab, Shanghai, China"],"raw_orcid":"https://orcid.org/0000-0002-2768-4540","affiliations":[{"raw_affiliation_string":"Amazon Shanghai AI Lab, Shanghai, China","institution_ids":["https://openalex.org/I4391012619"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5057909000","display_name":"Minjie Wang","orcid":"https://orcid.org/0009-0009-8156-1179"},"institutions":[{"id":"https://openalex.org/I4391012619","display_name":"Shanghai Artificial Intelligence Laboratory","ror":"https://ror.org/03wkvpx79","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4391012619"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Minjie Wang","raw_affiliation_strings":["Amazon Shanghai AI Lab, Shanghai, China"],"raw_orcid":"https://orcid.org/0009-0009-8156-1179","affiliations":[{"raw_affiliation_string":"Amazon Shanghai AI Lab, Shanghai, China","institution_ids":["https://openalex.org/I4391012619"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"5420","last_page":"5424"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.9995999932289124,"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":0.9995999932289124,"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":0.9994999766349792,"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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9900000095367432,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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":0.7536876201629639},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.4832097291946411},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.42861804366111755}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7536876201629639},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4832097291946411},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.42861804366111755}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3627673.3679153","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3627673.3679153","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 33rd ACM International Conference on Information and Knowledge Management","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education","score":0.6600000262260437}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":12,"referenced_works":["https://openalex.org/W2182353144","https://openalex.org/W2295598076","https://openalex.org/W2295739661","https://openalex.org/W2509235963","https://openalex.org/W3009186105","https://openalex.org/W3013995528","https://openalex.org/W4212774754","https://openalex.org/W4221055872","https://openalex.org/W4382246105","https://openalex.org/W4390043316","https://openalex.org/W4391494845","https://openalex.org/W6969259846"],"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":{"Crafting":[0],"effective":[1],"features":[2,94,104,120],"is":[3],"a":[4,50,76,84,130],"crucial":[5],"yet":[6],"labor-intensive":[7],"and":[8,123,138],"domain-specific":[9],"task":[10],"within":[11],"machine":[12],"learning":[13],"pipelines.":[14],"Fortunately,":[15],"recent":[16],"advancements":[17],"in":[18,26,66,163,190],"Large":[19],"Language":[20],"Models":[21],"(LLMs)":[22],"have":[23,151],"shown":[24],"promise":[25],"automating":[27],"various":[28],"data":[29],"science":[30],"tasks,":[31],"including":[32,91],"feature":[33,67],"engineering.":[34,68],"But":[35],"despite":[36],"this":[37,71,184],"potential,":[38],"evaluations":[39],"thus":[40],"far":[41],"are":[42],"primarily":[43],"based":[44],"on":[45,109,198],"the":[46,164,174,179],"end":[47],"performance":[48,112],"of":[49,134,173],"complete":[51],"ML":[52],"pipeline,":[53],"providing":[54],"limited":[55],"insight":[56],"into":[57,145],"precisely":[58],"how":[59],"LLMs":[60,137,149,167,193],"behave":[61],"relative":[62],"to":[63,187],"human":[64,139],"experts":[65],"To":[69],"address":[70],"gap,":[72],"we":[73,159],"propose":[74],"ELF-Gym,":[75],"framework":[77],"for":[78,153,208],"Evaluating":[79],"LLM-generated":[80,103],"Features.":[81],"We":[82],"curated":[83],"new":[85],"dataset":[86],"from":[87],"historical":[88],"Kaggle":[89],"competitions,":[90],"251":[92],"golden":[93,175],"used":[95],"by":[96,105],"top-performing":[97],"teams.":[98],"ELF-Gym":[99,158],"then":[100],"quantitatively":[101],"evaluates":[102],"measuring":[106],"their":[107,116],"impact":[108],"downstream":[110],"model":[111],"as":[113,115],"well":[114],"alignment":[117],"with":[118],"expert-crafted":[119],"through":[121],"semantic":[122],"functional":[124],"similarity":[125],"assessments.":[126],"This":[127],"approach":[128],"provides":[129],"more":[131,180],"comprehensive":[132],"evaluation":[133],"disparities":[135],"between":[136],"experts,":[140],"while":[141],"offering":[142],"valuable":[143],"insights":[144],"specific":[146],"areas":[147],"where":[148],"may":[150,194],"room":[152],"improvement.":[154,209],"For":[155],"example,":[156],"using":[157],"empirically":[160],"demonstrate":[161],"that,":[162],"best-case":[165],"scenario,":[166],"can":[168],"semantically":[169],"capture":[170],"approximately":[171],"56%":[172],"features,":[176,203],"but":[177],"at":[178],"demanding":[181],"implementation":[182],"level":[183],"overlap":[185],"drops":[186],"13%.":[188],"Moreover,":[189],"other":[191],"cases":[192],"fail":[195],"completely,":[196],"particularly":[197],"datasets":[199],"that":[200],"require":[201],"complex":[202],"indicating":[204],"broad":[205],"potential":[206],"pathways":[207]},"counts_by_year":[{"year":2026,"cited_by_count":2}],"updated_date":"2026-07-22T07:51:19.307946","created_date":"2025-10-10T00:00:00"}