{"id":"https://openalex.org/W4416437566","doi":"https://doi.org/10.18653/v1/2026.acl-long.1556","title":"UniDataBench: Evaluating Data Analytics Agents Across Structured and Unstructured Data","display_name":"UniDataBench: Evaluating Data Analytics Agents Across Structured and Unstructured Data","publication_year":2026,"publication_date":"2026-01-01","ids":{"openalex":"https://openalex.org/W4416437566","doi":"https://doi.org/10.18653/v1/2026.acl-long.1556"},"language":null,"primary_location":{"id":"doi:10.18653/v1/2026.acl-long.1556","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.acl-long.1556","pdf_url":"https://aclanthology.org/2026.acl-long.1556.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 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)","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.acl-long.1556.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5110683296","display_name":"H Weng","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Han Weng","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100712549","display_name":"Zhou Liu","orcid":"https://orcid.org/0000-0002-4651-1370"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhou Liu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5077688051","display_name":"Yuanfeng Song","orcid":"https://orcid.org/0000-0003-2221-9807"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yuanfeng Song","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5035051165","display_name":"Xiao\u2010Ming Yin","orcid":"https://orcid.org/0000-0002-8576-6093"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xiaoming Yin","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5036210249","display_name":"Xing Chen","orcid":"https://orcid.org/0000-0001-9028-5342"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xing Chen","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5008772211","display_name":"Wentao Zhang","orcid":"https://orcid.org/0000-0002-7532-5550"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wentao Zhang","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":0.01529582,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"33755","last_page":"33780"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11719","display_name":"Data Quality and Management","score":0.6459000110626221,"subfield":{"id":"https://openalex.org/subfields/1803","display_name":"Management Science and Operations Research"},"field":{"id":"https://openalex.org/fields/18","display_name":"Decision Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},"topics":[{"id":"https://openalex.org/T11719","display_name":"Data Quality and Management","score":0.6459000110626221,"subfield":{"id":"https://openalex.org/subfields/1803","display_name":"Management Science and Operations Research"},"field":{"id":"https://openalex.org/fields/18","display_name":"Decision Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T14347","display_name":"Big Data and Digital Economy","score":0.02889999933540821,"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/T11891","display_name":"Big Data and Business Intelligence","score":0.02539999969303608,"subfield":{"id":"https://openalex.org/subfields/1404","display_name":"Management Information Systems"},"field":{"id":"https://openalex.org/fields/14","display_name":"Business, Management and Accounting"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/nosql","display_name":"NoSQL","score":0.7457000017166138},{"id":"https://openalex.org/keywords/unstructured-data","display_name":"Unstructured data","score":0.707099974155426},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.630299985408783},{"id":"https://openalex.org/keywords/variety","display_name":"Variety (cybernetics)","score":0.6273999810218811},{"id":"https://openalex.org/keywords/analytics","display_name":"Analytics","score":0.6175000071525574},{"id":"https://openalex.org/keywords/pipeline","display_name":"Pipeline (software)","score":0.5935999751091003},{"id":"https://openalex.org/keywords/relational-database","display_name":"Relational database","score":0.5156999826431274},{"id":"https://openalex.org/keywords/big-data","display_name":"Big data","score":0.4526999890804291}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8314999938011169},{"id":"https://openalex.org/C2779599972","wikidata":"https://www.wikidata.org/wiki/Q82231","display_name":"NoSQL","level":3,"score":0.7457000017166138},{"id":"https://openalex.org/C2781252014","wikidata":"https://www.wikidata.org/wiki/Q1141900","display_name":"Unstructured data","level":3,"score":0.707099974155426},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.630299985408783},{"id":"https://openalex.org/C136197465","wikidata":"https://www.wikidata.org/wiki/Q1729295","display_name":"Variety (cybernetics)","level":2,"score":0.6273999810218811},{"id":"https://openalex.org/C79158427","wikidata":"https://www.wikidata.org/wiki/Q485396","display_name":"Analytics","level":2,"score":0.6175000071525574},{"id":"https://openalex.org/C43521106","wikidata":"https://www.wikidata.org/wiki/Q2165493","display_name":"Pipeline (software)","level":2,"score":0.5935999751091003},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.5450999736785889},{"id":"https://openalex.org/C5655090","wikidata":"https://www.wikidata.org/wiki/Q192588","display_name":"Relational database","level":2,"score":0.5156999826431274},{"id":"https://openalex.org/C75684735","wikidata":"https://www.wikidata.org/wiki/Q858810","display_name":"Big data","level":2,"score":0.4526999890804291},{"id":"https://openalex.org/C2767350","wikidata":"https://www.wikidata.org/wiki/Q6662173","display_name":"Business intelligence","level":2,"score":0.45179998874664307},{"id":"https://openalex.org/C175801342","wikidata":"https://www.wikidata.org/wiki/Q1988917","display_name":"Data analysis","level":2,"score":0.4207000136375427},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.39640000462532043},{"id":"https://openalex.org/C40077939","wikidata":"https://www.wikidata.org/wiki/Q2336004","display_name":"Semi-structured data","level":3,"score":0.37610000371932983},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.3732999861240387},{"id":"https://openalex.org/C138958017","wikidata":"https://www.wikidata.org/wiki/Q190087","display_name":"Data type","level":2,"score":0.35350000858306885},{"id":"https://openalex.org/C67186912","wikidata":"https://www.wikidata.org/wiki/Q367664","display_name":"Data modeling","level":2,"score":0.3450999855995178},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.32440000772476196},{"id":"https://openalex.org/C120567893","wikidata":"https://www.wikidata.org/wiki/Q1582085","display_name":"Knowledge extraction","level":2,"score":0.323199987411499},{"id":"https://openalex.org/C37952496","wikidata":"https://www.wikidata.org/wiki/Q5001829","display_name":"Business analytics","level":4,"score":0.3222000002861023},{"id":"https://openalex.org/C47487241","wikidata":"https://www.wikidata.org/wiki/Q5227230","display_name":"Data access","level":2,"score":0.2888999879360199},{"id":"https://openalex.org/C43126263","wikidata":"https://www.wikidata.org/wiki/Q128751","display_name":"Source code","level":2,"score":0.28110000491142273},{"id":"https://openalex.org/C40207289","wikidata":"https://www.wikidata.org/wiki/Q755662","display_name":"Relational model","level":3,"score":0.27469998598098755},{"id":"https://openalex.org/C24394798","wikidata":"https://www.wikidata.org/wiki/Q192588","display_name":"Relational database management system","level":3,"score":0.2502000033855438}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.18653/v1/2026.acl-long.1556","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.acl-long.1556","pdf_url":"https://aclanthology.org/2026.acl-long.1556.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 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2511.01625","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2511.01625","pdf_url":"https://arxiv.org/pdf/2511.01625","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-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2511.01625","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2511.01625","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":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"doi:10.18653/v1/2026.acl-long.1556","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.acl-long.1556","pdf_url":"https://aclanthology.org/2026.acl-long.1556.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 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G2981796383","display_name":null,"funder_award_id":"62402016","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G4572520933","display_name":null,"funder_award_id":"92470121","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"},{"id":"https://openalex.org/F4320321106","display_name":"Ministry of Education of the People's Republic of China","ror":"https://ror.org/01mv9t934"},{"id":"https://openalex.org/F4320324787","display_name":"Peking University","ror":"https://ror.org/02v51f717"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4416437566.pdf","grobid_xml":"https://content.openalex.org/works/W4416437566.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"In":[0],"real-world":[1,105,184],"business":[2,106],"environments,":[3],"data":[4,46,63,69,85,121,150,180],"is":[5,30,72],"stored":[6],"in":[7,39,66,183],"a":[8,54,81,110,135,173],"variety":[9],"of":[10,62,179],"sources,":[11],"including":[12],"structured":[13],"relational":[14,96],"databases,":[15,17,97],"semi-structured":[16],"and":[18,100,108,125,129,159,169],"unstructured":[19],"files.The":[20],"ability":[21],"to":[22,32,58,83,103,164],"extract":[23,123,165],"reasonable":[24],"insights":[25],"across":[26,43],"these":[27,44],"diverse":[28,45,68,93,149],"sources":[29,151],"integral":[31],"data-driven":[33],"decisionmaking.Existing":[34],"benchmarks,":[35],"however,":[36],"are":[37],"limited":[38],"assessing":[40],"agents'":[41],"capabilities":[42],"types.To":[47],"address":[48],"this":[49],"gap,":[50],"we":[51,133],"introduce":[52],"UniDataBench,":[53,132],"multi-source":[55],"benchmark":[56,168],"designed":[57],"evaluate":[59],"the":[60,177],"performance":[61],"analytics":[64,181],"agents":[65,117,182],"handling":[67],"sources.Specifically,":[70],"UniDataBench":[71],"constructed":[73],"based":[74],"on":[75,131],"real-life":[76],"industry":[77],"analysis":[78,147],"reports,":[79],"employing":[80],"pipeline":[82],"synthesize":[84],"that":[86,144],"aligns":[87],"with":[88],"authentic":[89],"analytical":[90],"trends.It":[91],"encompasses":[92],"datasets":[94],"spanning":[95],"CSV":[98],"files,":[99],"NoSQL":[101],"stores":[102],"reflect":[104],"settings,":[107],"provides":[109],"unified":[111],"framework":[112,174],"for":[113,175],"evaluating":[114],"how":[115],"effectively":[116],"can":[118],"explore":[119],"multiple":[120],"formats,":[122],"insights,":[124],"generate":[126],"meaningful":[127],"summaries":[128],"recommendations.Based":[130],"propose":[134],"novel":[136],"LLM-based":[137],"agent":[138,143,170],"named":[139],"ReActInsight,":[140],"an":[141],"autonomous":[142],"performs":[145],"end-to-end":[146],"over":[148],"by":[152],"automatically":[153],"discovering":[154],"cross-source":[155],"linkages,":[156],"decomposing":[157],"goals,":[158],"generating":[160],"robust,":[161],"self-correcting":[162],"code":[163],"actionable":[166],"insights.Our":[167],"together":[171],"provide":[172],"facilitating":[176],"development":[178],"applications.*":[185],"Equal":[186],"contribution.":[187]},"counts_by_year":[],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-11-06T00:00:00"}