{"id":"https://openalex.org/W4407780297","doi":"https://doi.org/10.18653/v1/2026.findings-acl.181","title":"DataSciBench: An LLM Agent Benchmark for Data Science","display_name":"DataSciBench: An LLM Agent Benchmark for Data Science","publication_year":2026,"publication_date":"2026-01-01","ids":{"openalex":"https://openalex.org/W4407780297","doi":"https://doi.org/10.18653/v1/2026.findings-acl.181"},"language":"en","primary_location":{"id":"doi:10.18653/v1/2026.findings-acl.181","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.findings-acl.181","pdf_url":"https://aclanthology.org/2026.findings-acl.181.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":"Findings of the Association for Computational Linguistics: ACL 2026","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://aclanthology.org/2026.findings-acl.181.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5100456041","display_name":"Dan Zhang","orcid":"https://orcid.org/0000-0002-7295-4837"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Dan Zhang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5093734261","display_name":"Sining Zhoubian","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Sining Zhoubian","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5109298919","display_name":"Cai Min","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Min Cai","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5112822440","display_name":"Fanghu Li","orcid":"https://orcid.org/0009-0001-6582-9165"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Fengzu Li","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5015083074","display_name":"Likun Yang","orcid":"https://orcid.org/0000-0001-6737-8399"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Lekang Yang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100391896","display_name":"Wei Wang","orcid":"https://orcid.org/0000-0002-1717-5785"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wei Wang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5113070784","display_name":"Tian Dong","orcid":"https://orcid.org/0009-0009-4671-8396"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Tianjiao Dong","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5060639952","display_name":"Ziniu Hu","orcid":"https://orcid.org/0009-0007-8818-739X"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ziniu Hu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5089631680","display_name":"Jie Tang","orcid":"https://orcid.org/0000-0003-0619-0338"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jie Tang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5103936369","display_name":"Yisong Yue","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yisong Yue","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"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":0.00184973,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"3685","last_page":"3728"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10538","display_name":"Data Mining Algorithms and Applications","score":0.9276999831199646,"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"}},"topics":[{"id":"https://openalex.org/T10538","display_name":"Data Mining Algorithms and Applications","score":0.9276999831199646,"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/benchmark","display_name":"Benchmark (surveying)","score":0.8410588502883911},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.44331610202789307},{"id":"https://openalex.org/keywords/data-science","display_name":"Data science","score":0.36013472080230713},{"id":"https://openalex.org/keywords/cartography","display_name":"Cartography","score":0.10741114616394043},{"id":"https://openalex.org/keywords/geography","display_name":"Geography","score":0.09317153692245483}],"concepts":[{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.8410588502883911},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.44331610202789307},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.36013472080230713},{"id":"https://openalex.org/C58640448","wikidata":"https://www.wikidata.org/wiki/Q42515","display_name":"Cartography","level":1,"score":0.10741114616394043},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.09317153692245483}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.18653/v1/2026.findings-acl.181","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.findings-acl.181","pdf_url":"https://aclanthology.org/2026.findings-acl.181.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":"Findings of the Association for Computational Linguistics: ACL 2026","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2502.13897","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2502.13897","pdf_url":"https://arxiv.org/pdf/2502.13897","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,"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":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2502.13897","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2502.13897","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,"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":null,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"doi:10.18653/v1/2026.findings-acl.181","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.findings-acl.181","pdf_url":"https://aclanthology.org/2026.findings-acl.181.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":"Findings of the Association for Computational Linguistics: ACL 2026","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G6694531218","display_name":null,"funder_award_id":"62425601","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G758127907","display_name":null,"funder_award_id":"62406163","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4407780297.pdf","grobid_xml":"https://content.openalex.org/works/W4407780297.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2899084033","https://openalex.org/W2748952813","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"],"abstract_inverted_index":{"This":[0],"paper":[1],"presents":[2],"DataSciBench,":[3],"a":[4,52],"comprehensive":[5],"benchmark":[6],"for":[7],"evaluating":[8],"Large":[9],"Language":[10],"Models":[11],"(LLMs)":[12],"in":[13],"data":[14],"science.Unlike":[15],"existing":[16],"benchmarks":[17],"limited":[18],"to":[19,63],"single":[20],"task,":[21],"simple":[22],"evaluation":[23,42],"metrics,":[24,122],"and":[25,37,44,60,69,86,99,111],"readily":[26],"available":[27],"ground":[28],"truth":[29],"(GT),":[30],"DataSciBench":[31],"is":[32],"built":[33],"on":[34],"curated,":[35],"natural,":[36],"challenging":[38],"prompts":[39],"with":[40,123],"complex":[41],"criteria":[43],"uncertain":[45],"GT.To":[46],"bridge":[47],"the":[48],"gap,":[49],"we":[50,73],"develop":[51],"semi-automated":[53],"GT":[54],"generation":[55],"pipeline,":[56],"integrating":[57],"LLM-based":[58],"selfconsistency":[59],"human":[61],"verification":[62],"ensure":[64],"accuracy,":[65],"predefined":[66],"task":[67],"types,":[68],"aggregate":[70],"functions":[71],"(metrics).Furthermore,":[72],"introduce":[74],"an":[75],"innovative":[76],"Intention-Function-Code":[77],"(IFC)":[78],"framework,":[79],"assessing":[80],"code":[81,97],"execution":[82],"outcomes":[83],"through":[84],"metrics":[85],"programmatic":[87],"rules.Evaluating":[88],"26":[89],"models":[90,116],"(8":[91],"API-based,":[92],"8":[93],"open-source":[94,118],"general,":[95],"9":[96],"generation,":[98],"1":[100],"agentic":[101],"models),":[102],"our":[103],"approach":[104],"offers":[105],"rigorous":[106],"insights":[107],"into":[108],"LLM":[109],"strengths":[110],"weaknesses.Experimental":[112],"results":[113],"show":[114],"API-based":[115],"outperform":[117],"counterparts":[119],"across":[120],"all":[121],"DeepAnalyze-8B":[124],"leading":[125],"among":[126],"open-sourced":[127],"models.We":[128],"release":[129]},"counts_by_year":[],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}