{"id":"https://openalex.org/W4391885762","doi":"https://doi.org/10.1109/icaic60265.2024.10433803","title":"DataAgent: Evaluating Large Language Models\u2019 Ability to Answer Zero-Shot, Natural Language Queries","display_name":"DataAgent: Evaluating Large Language Models\u2019 Ability to Answer Zero-Shot, Natural Language Queries","publication_year":2024,"publication_date":"2024-02-07","ids":{"openalex":"https://openalex.org/W4391885762","doi":"https://doi.org/10.1109/icaic60265.2024.10433803"},"language":"en","primary_location":{"id":"doi:10.1109/icaic60265.2024.10433803","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/icaic60265.2024.10433803","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE 3rd International Conference on AI in Cybersecurity (ICAIC)","raw_type":"proceedings-article"},"type":"preprint","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2404.00188","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5005790108","display_name":"Manit Mishra","orcid":"https://orcid.org/0000-0002-2813-0064"},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Manit Mishra","raw_affiliation_strings":["Irvington High School,Fremont,United States","Irvington High School, Fremont, United States"],"affiliations":[{"raw_affiliation_string":"Irvington High School,Fremont,United States","institution_ids":[]},{"raw_affiliation_string":"Irvington High School, Fremont, United States","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5108314150","display_name":"Abderrahman Braham","orcid":null},"institutions":[{"id":"https://openalex.org/I8636806","display_name":"University of Sousse","ror":"https://ror.org/00dmpgj58","country_code":"TN","type":"education","lineage":["https://openalex.org/I8636806"]}],"countries":["TN"],"is_corresponding":false,"raw_author_name":"Abderrahman Braham","raw_affiliation_strings":["Pioneer High School,Sousse,Tunisia","Pioneer High School, Sousse, Tunisia"],"affiliations":[{"raw_affiliation_string":"Pioneer High School,Sousse,Tunisia","institution_ids":["https://openalex.org/I8636806"]},{"raw_affiliation_string":"Pioneer High School, Sousse, Tunisia","institution_ids":["https://openalex.org/I8636806"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5093943211","display_name":"Charles Marsom","orcid":null},"institutions":[{"id":"https://openalex.org/I84218800","display_name":"University of California, Davis","ror":"https://ror.org/05rrcem69","country_code":"US","type":"education","lineage":["https://openalex.org/I84218800"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Charles Marsom","raw_affiliation_strings":["Davis Senior High School,Davis,United States","Davis Senior High School, Davis, United States"],"affiliations":[{"raw_affiliation_string":"Davis Senior High School,Davis,United States","institution_ids":["https://openalex.org/I84218800"]},{"raw_affiliation_string":"Davis Senior High School, Davis, United States","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5109365172","display_name":"Bryan Chung","orcid":null},"institutions":[{"id":"https://openalex.org/I4210133860","display_name":"Windsor Dermatology","ror":"https://ror.org/03m5z5h02","country_code":"US","type":"healthcare","lineage":["https://openalex.org/I4210133860"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Bryan Chung","raw_affiliation_strings":["The Loomis Chaffee School,Windsor,United States","The Loomis Chaffee School, Windsor, United States"],"affiliations":[{"raw_affiliation_string":"The Loomis Chaffee School,Windsor,United States","institution_ids":["https://openalex.org/I4210133860"]},{"raw_affiliation_string":"The Loomis Chaffee School, Windsor, United States","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5113972002","display_name":"G. R. Griffin","orcid":null},"institutions":[{"id":"https://openalex.org/I872719","display_name":"Bellarmine University","ror":"https://ror.org/04p81nz21","country_code":"US","type":"education","lineage":["https://openalex.org/I872719"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Gavin Griffin","raw_affiliation_strings":["Bellarmine College Preparatory,Sunnyvale,United States","Bellarmine College Preparatory, Sunnyvale, United States"],"affiliations":[{"raw_affiliation_string":"Bellarmine College Preparatory,Sunnyvale,United States","institution_ids":["https://openalex.org/I872719"]},{"raw_affiliation_string":"Bellarmine College Preparatory, Sunnyvale, United States","institution_ids":["https://openalex.org/I872719"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5093943212","display_name":"Dakshesh Sidnerlikar","orcid":null},"institutions":[{"id":"https://openalex.org/I102322142","display_name":"Rutgers, The State University of New Jersey","ror":"https://ror.org/05vt9qd57","country_code":"US","type":"education","lineage":["https://openalex.org/I102322142"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Dakshesh Sidnerlikar","raw_affiliation_strings":["Rutgers University,New Brunswick,United States","Rutgers University, New Brunswick, United States"],"affiliations":[{"raw_affiliation_string":"Rutgers University,New Brunswick,United States","institution_ids":["https://openalex.org/I102322142"]},{"raw_affiliation_string":"Rutgers University, New Brunswick, United States","institution_ids":["https://openalex.org/I102322142"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5092116368","display_name":"Chatanya Sarin","orcid":null},"institutions":[{"id":"https://openalex.org/I872719","display_name":"Bellarmine University","ror":"https://ror.org/04p81nz21","country_code":"US","type":"education","lineage":["https://openalex.org/I872719"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Chatanya Sarin","raw_affiliation_strings":["Bellarmine College Preparatory,Sunnyvale,United States","Bellarmine College Preparatory, Sunnyvale, United States"],"affiliations":[{"raw_affiliation_string":"Bellarmine College Preparatory,Sunnyvale,United States","institution_ids":["https://openalex.org/I872719"]},{"raw_affiliation_string":"Bellarmine College Preparatory, Sunnyvale, United States","institution_ids":["https://openalex.org/I872719"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5104241393","display_name":"Arjun Rajaram","orcid":"https://orcid.org/0000-0001-7016-1617"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Arjun Rajaram","raw_affiliation_strings":["University of Maryland,Frisco,United States","University of Maryland, Frisco, United States"],"affiliations":[{"raw_affiliation_string":"University of Maryland,Frisco,United States","institution_ids":[]},{"raw_affiliation_string":"University of Maryland, Frisco, United States","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":8,"corresponding_author_ids":["https://openalex.org/A5005790108"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.0692,"has_fulltext":true,"cited_by_count":3,"citation_normalized_percentile":{"value":0.76040493,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"5"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12127","display_name":"Software System Performance and Reliability","score":0.9940000176429749,"subfield":{"id":"https://openalex.org/subfields/1705","display_name":"Computer Networks and Communications"},"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/T12127","display_name":"Software System Performance and Reliability","score":0.9940000176429749,"subfield":{"id":"https://openalex.org/subfields/1705","display_name":"Computer Networks and Communications"},"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/T10260","display_name":"Software Engineering Research","score":0.9896000027656555,"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"}},{"id":"https://openalex.org/T12535","display_name":"Machine Learning and Data Classification","score":0.9847000241279602,"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":0.8250042200088501},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.7438108921051025},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5439654588699341},{"id":"https://openalex.org/keywords/coding","display_name":"Coding (social sciences)","score":0.5268401503562927},{"id":"https://openalex.org/keywords/natural-language","display_name":"Natural language","score":0.5057356357574463},{"id":"https://openalex.org/keywords/source-code","display_name":"Source code","score":0.4912664294242859},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.48114287853240967},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.45325759053230286},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.4248698353767395},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.4132651090621948},{"id":"https://openalex.org/keywords/code","display_name":"Code (set theory)","score":0.41090402007102966},{"id":"https://openalex.org/keywords/data-science","display_name":"Data science","score":0.37766146659851074},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.3222547471523285},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.13807642459869385}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8250042200088501},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.7438108921051025},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5439654588699341},{"id":"https://openalex.org/C179518139","wikidata":"https://www.wikidata.org/wiki/Q5140297","display_name":"Coding (social sciences)","level":2,"score":0.5268401503562927},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.5057356357574463},{"id":"https://openalex.org/C43126263","wikidata":"https://www.wikidata.org/wiki/Q128751","display_name":"Source code","level":2,"score":0.4912664294242859},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.48114287853240967},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.45325759053230286},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.4248698353767395},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.4132651090621948},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.41090402007102966},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.37766146659851074},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.3222547471523285},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.13807642459869385},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.0},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0},{"id":"https://openalex.org/C13280743","wikidata":"https://www.wikidata.org/wiki/Q131089","display_name":"Geodesy","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/icaic60265.2024.10433803","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/icaic60265.2024.10433803","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE 3rd International Conference on AI in Cybersecurity (ICAIC)","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2404.00188","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2404.00188","pdf_url":"https://arxiv.org/pdf/2404.00188","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"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"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2404.00188","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2404.00188","pdf_url":"https://arxiv.org/pdf/2404.00188","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"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"},"sustainable_development_goals":[{"display_name":"Quality Education","score":0.5099999904632568,"id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4391885762.pdf","grobid_xml":"https://content.openalex.org/works/W4391885762.grobid-xml"},"referenced_works_count":7,"referenced_works":["https://openalex.org/W2899709844","https://openalex.org/W3139250374","https://openalex.org/W4213074563","https://openalex.org/W4221143046","https://openalex.org/W4224912544","https://openalex.org/W4308244910","https://openalex.org/W4353112996"],"related_works":["https://openalex.org/W2378211422","https://openalex.org/W4321353415","https://openalex.org/W2745001401","https://openalex.org/W2130974462","https://openalex.org/W2028665553","https://openalex.org/W2086519370","https://openalex.org/W4246352526","https://openalex.org/W2121910908","https://openalex.org/W915438175","https://openalex.org/W4230315250"],"abstract_inverted_index":{"Conventional":[0],"processes":[1],"for":[2,142,147],"analyzing":[3],"datasets":[4,76],"and":[5,12,21,36,59,97,99,133],"extracting":[6],"meaningful":[7],"information":[8],"are":[9],"often":[10],"time-consuming":[11],"laborious.":[13],"Previous":[14],"work":[15],"has":[16],"identified":[17],"manual,":[18],"repetitive":[19],"coding":[20],"data":[22,29,85,108,150],"collection":[23],"as":[24,46,93],"major":[25],"obstacles":[26],"that":[27,52],"hinder":[28],"scientists":[30],"from":[31,62],"undertaking":[32],"more":[33],"nuanced":[34],"labor":[35],"high-level":[37],"projects.":[38],"To":[39],"combat":[40],"this,":[41],"we":[42],"evaluated":[43],"OpenAI\u2019s":[44],"GPT-3.5":[45],"a":[47,63,71,106,127],"\"Language":[48],"Data":[49],"Scientist\"":[50],"(LDS)":[51],"can":[53],"extrapolate":[54],"key":[55],"findings,":[56],"including":[57,84,130],"correlations":[58],"basic":[60],"information,":[61],"given":[64,107,128],"dataset.":[65,115],"The":[66,116],"model":[67],"was":[68,100],"tested":[69],"on":[70],"diverse":[72],"set":[73],"of":[74],"benchmark":[75,114],"to":[77,112,124],"evaluate":[78],"its":[79],"performance":[80],"across":[81],"multiple":[82],"standards,":[83],"science":[86,109],"code-generation":[87],"based":[88],"tasks":[89],"involving":[90],"libraries":[91],"such":[92],"NumPy,":[94],"Pandas,":[95],"Scikit-Learn,":[96],"TensorFlow,":[98],"broadly":[101],"successful":[102],"in":[103],"correctly":[104],"answering":[105],"query":[110],"related":[111],"the":[113],"LDS":[117],"used":[118],"various":[119],"novel":[120],"prompt":[121,135],"engineering":[122],"techniques":[123],"effectively":[125],"answer":[126],"question,":[129],"Chain-of-Thought":[131],"reinforcement":[132],"SayCan":[134],"engineering.":[136],"Our":[137],"findings":[138],"demonstrate":[139],"great":[140],"potential":[141],"leveraging":[143],"Large":[144],"Language":[145],"Models":[146],"low-level,":[148],"zero-shot":[149],"analysis.":[151]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":1}],"updated_date":"2026-03-20T23:20:44.827607","created_date":"2024-02-17T00:00:00"}