{"id":"https://openalex.org/W4416949683","doi":"https://doi.org/10.18653/v1/2026.findings-acl.1729","title":"InsightEval: An Expert-Curated Benchmark for Assessing Insight Discovery in LLM-Driven Data Agents","display_name":"InsightEval: An Expert-Curated Benchmark for Assessing Insight Discovery in LLM-Driven Data Agents","publication_year":2026,"publication_date":"2026-01-01","ids":{"openalex":"https://openalex.org/W4416949683","doi":"https://doi.org/10.18653/v1/2026.findings-acl.1729"},"language":null,"primary_location":{"id":"doi:10.18653/v1/2026.findings-acl.1729","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.findings-acl.1729","pdf_url":"https://aclanthology.org/2026.findings-acl.1729.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.1729.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5067669655","display_name":"Zhenghao Zhu","orcid":"https://orcid.org/0000-0001-8443-6095"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhenghao Zhu","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/A5100725089","display_name":"Xin Chen","orcid":"https://orcid.org/0009-0007-2070-141X"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xing Chen","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103233885","display_name":"Chengzhong Liu","orcid":"https://orcid.org/0000-0002-6130-7773"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Chengzhong Liu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":null,"display_name":"Cui Yakun","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Cui Yakun","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5052597827","display_name":"Caleb Chen Cao","orcid":"https://orcid.org/0000-0002-8050-2486"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Caleb Chen Cao","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5077447568","display_name":"Sirui Han","orcid":"https://orcid.org/0000-0001-9461-8538"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Sirui Han","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5045081171","display_name":"Yike Guo","orcid":"https://orcid.org/0000-0002-3075-2161"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yike Guo","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":0.00139431,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"34632","last_page":"34656"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11948","display_name":"Machine Learning in Materials Science","score":0.11069999635219574,"subfield":{"id":"https://openalex.org/subfields/2505","display_name":"Materials Chemistry"},"field":{"id":"https://openalex.org/fields/25","display_name":"Materials Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T11948","display_name":"Machine Learning in Materials Science","score":0.11069999635219574,"subfield":{"id":"https://openalex.org/subfields/2505","display_name":"Materials Chemistry"},"field":{"id":"https://openalex.org/fields/25","display_name":"Materials Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T13083","display_name":"Advanced Text Analysis Techniques","score":0.05979999899864197,"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/T11273","display_name":"Advanced Graph Neural Networks","score":0.05810000002384186,"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/pipeline","display_name":"Pipeline (software)","score":0.5861999988555908},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.569100022315979},{"id":"https://openalex.org/keywords/construct","display_name":"Construct (python library)","score":0.5418000221252441},{"id":"https://openalex.org/keywords/metric","display_name":"Metric (unit)","score":0.5126000046730042},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.48170000314712524},{"id":"https://openalex.org/keywords/quality","display_name":"Quality (philosophy)","score":0.44609999656677246},{"id":"https://openalex.org/keywords/exploratory-data-analysis","display_name":"Exploratory data analysis","score":0.4309000074863434}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7595999836921692},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.6819000244140625},{"id":"https://openalex.org/C43521106","wikidata":"https://www.wikidata.org/wiki/Q2165493","display_name":"Pipeline (software)","level":2,"score":0.5861999988555908},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.569100022315979},{"id":"https://openalex.org/C2780801425","wikidata":"https://www.wikidata.org/wiki/Q5164392","display_name":"Construct (python library)","level":2,"score":0.5418000221252441},{"id":"https://openalex.org/C176217482","wikidata":"https://www.wikidata.org/wiki/Q860554","display_name":"Metric (unit)","level":2,"score":0.5126000046730042},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.48170000314712524},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.44609999656677246},{"id":"https://openalex.org/C120894424","wikidata":"https://www.wikidata.org/wiki/Q1322871","display_name":"Exploratory data analysis","level":2,"score":0.4309000074863434},{"id":"https://openalex.org/C3018260909","wikidata":"https://www.wikidata.org/wiki/Q1322871","display_name":"Exploratory analysis","level":2,"score":0.37439998984336853},{"id":"https://openalex.org/C2780009758","wikidata":"https://www.wikidata.org/wiki/Q6804172","display_name":"Measure (data warehouse)","level":2,"score":0.37310001254081726},{"id":"https://openalex.org/C24756922","wikidata":"https://www.wikidata.org/wiki/Q1757694","display_name":"Data quality","level":3,"score":0.34380000829696655},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.31450000405311584},{"id":"https://openalex.org/C120567893","wikidata":"https://www.wikidata.org/wiki/Q1582085","display_name":"Knowledge extraction","level":2,"score":0.30640000104904175},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.29109999537467957},{"id":"https://openalex.org/C2780598303","wikidata":"https://www.wikidata.org/wiki/Q65921492","display_name":"Flexibility (engineering)","level":2,"score":0.2669999897480011},{"id":"https://openalex.org/C86251818","wikidata":"https://www.wikidata.org/wiki/Q816754","display_name":"Benchmarking","level":2,"score":0.257999986410141},{"id":"https://openalex.org/C207267971","wikidata":"https://www.wikidata.org/wiki/Q120208","display_name":"Emerging technologies","level":2,"score":0.25200000405311584},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.2517000138759613}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.18653/v1/2026.findings-acl.1729","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.findings-acl.1729","pdf_url":"https://aclanthology.org/2026.findings-acl.1729.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:2511.22884","is_oa":true,"landing_page_url":"https://arxiv.org/abs/2511.22884","pdf_url":"https://arxiv.org/pdf/2511.22884","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.2511.22884","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2511.22884","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.findings-acl.1729","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.findings-acl.1729","pdf_url":"https://aclanthology.org/2026.findings-acl.1729.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":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4416949683.pdf","grobid_xml":"https://content.openalex.org/works/W4416949683.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Data":[0],"analysis":[1,26],"has":[2],"become":[3],"an":[4],"indispensable":[5],"part":[6],"of":[7,34,49,65,92,97,140],"scientific":[8],"research.To":[9],"discover":[10],"the":[11,32,66,90,95,137],"latent":[12],"knowledge":[13],"and":[14,39,43,83,94,108,154],"insights":[15],"hidden":[16],"within":[17],"massive":[18],"datasets,":[19],"we":[20,102,118,146],"need":[21],"to":[22,27,123,135,159],"perform":[23],"deep":[24],"exploratory":[25,138],"realize":[28],"their":[29],"full":[30],"value.With":[31],"advent":[33],"large":[35],"language":[36],"models":[37],"(LLMs)":[38],"multi-agent":[40],"systems,":[41],"more":[42,44],"researchers":[45],"are":[46,56],"making":[47],"use":[48],"these":[50,100],"technologies":[51],"for":[52,59,112],"insight":[53,61,115,152],"discovery.However,":[54],"there":[55],"few":[57],"benchmarks":[58],"evaluating":[60],"discovery":[62,153],"capabilities.As":[63],"one":[64],"most":[67],"comprehensive":[68],"existing":[69],"frameworks,":[70],"InsightBench":[71],"also":[72],"suffers":[73],"from":[74],"many":[75],"critical":[76],"flaws:":[77],"format":[78],"inconsistencies,":[79],"poorly":[80],"conceived":[81],"objectives,":[82],"redundant":[84],"insights.These":[85],"issues":[86],"may":[87],"significantly":[88],"affect":[89],"quality":[91],"data":[93],"evaluation":[96],"agents.To":[98],"address":[99],"issues,":[101],"thoroughly":[103],"investigate":[104],"shortcomings":[105],"in":[106,150,163],"Insight-Bench":[107],"propose":[109],"essential":[110],"criteria":[111],"a":[113,120,125,132],"highquality":[114],"benchmark.Regarding":[116],"this,":[117],"develop":[119],"data-curation":[121],"pipeline":[122],"construct":[124],"new":[126],"dataset":[127],"named":[128],"InsightEval.We":[129],"further":[130],"introduce":[131],"novel":[133],"metric":[134],"measure":[136],"performance":[139],"agents.Through":[141],"extensive":[142],"experiments":[143],"on":[144],"InsightEval,":[145],"highlight":[147],"prevailing":[148],"challenges":[149],"automated":[151],"raise":[155],"some":[156],"key":[157],"findings":[158],"guide":[160],"future":[161],"research":[162],"this":[164],"promising":[165],"direction.":[166]},"counts_by_year":[],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-12-03T00:00:00"}