{"id":"https://openalex.org/W7163168970","doi":"https://doi.org/10.48550/arxiv.2606.02334","title":"Less Is More? When Dataset Context Hurts LLM-Generated Dataset Descriptions","display_name":"Less Is More? When Dataset Context Hurts LLM-Generated Dataset Descriptions","publication_year":2026,"publication_date":"2026-06-01","ids":{"openalex":"https://openalex.org/W7163168970","doi":"https://doi.org/10.48550/arxiv.2606.02334"},"language":null,"primary_location":{"id":"doi:10.48550/arxiv.2606.02334","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2606.02334","pdf_url":null,"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":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"},"type":"preprint","indexed_in":["datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://doi.org/10.48550/arxiv.2606.02334","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5132964847","display_name":"Lisa-Yao Gan","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Gan, Lisa-Yao","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5014092907","display_name":"Arunav Das","orcid":"https://orcid.org/0009-0008-9989-1718"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Das, Arunav","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5137680919","display_name":"Johanna Walker","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Walker, Johanna","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5135963544","display_name":"Klaus Diepold","orcid":"https://orcid.org/0000-0003-0439-7511"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Diepold, Klaus","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5137650273","display_name":"Elena Simperl","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Simperl, Elena","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":null,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.20080000162124634,"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":0.20080000162124634,"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/T13702","display_name":"Machine Learning in Healthcare","score":0.19179999828338623,"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/T11719","display_name":"Data Quality and Management","score":0.08169999718666077,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/metadata","display_name":"Metadata","score":0.6699000000953674},{"id":"https://openalex.org/keywords/schema","display_name":"Schema (genetic algorithms)","score":0.664900004863739},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.460099995136261},{"id":"https://openalex.org/keywords/narrative","display_name":"Narrative","score":0.41909998655319214},{"id":"https://openalex.org/keywords/data-quality","display_name":"Data quality","score":0.40470001101493835},{"id":"https://openalex.org/keywords/natural-language","display_name":"Natural language","score":0.3984000086784363},{"id":"https://openalex.org/keywords/reuse","display_name":"Reuse","score":0.3912000060081482}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7275000214576721},{"id":"https://openalex.org/C93518851","wikidata":"https://www.wikidata.org/wiki/Q180160","display_name":"Metadata","level":2,"score":0.6699000000953674},{"id":"https://openalex.org/C52146309","wikidata":"https://www.wikidata.org/wiki/Q7431116","display_name":"Schema (genetic algorithms)","level":2,"score":0.664900004863739},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.460099995136261},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.42809998989105225},{"id":"https://openalex.org/C199033989","wikidata":"https://www.wikidata.org/wiki/Q1318295","display_name":"Narrative","level":2,"score":0.41909998655319214},{"id":"https://openalex.org/C24756922","wikidata":"https://www.wikidata.org/wiki/Q1757694","display_name":"Data quality","level":3,"score":0.40470001101493835},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.3984000086784363},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3953000009059906},{"id":"https://openalex.org/C206588197","wikidata":"https://www.wikidata.org/wiki/Q846574","display_name":"Reuse","level":2,"score":0.3912000060081482},{"id":"https://openalex.org/C12725497","wikidata":"https://www.wikidata.org/wiki/Q810247","display_name":"Baseline (sea)","level":2,"score":0.38929998874664307},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.3797000050544739},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.37470000982284546},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.36309999227523804},{"id":"https://openalex.org/C120936955","wikidata":"https://www.wikidata.org/wiki/Q2155640","display_name":"Empirical research","level":2,"score":0.3441999852657318},{"id":"https://openalex.org/C69075417","wikidata":"https://www.wikidata.org/wiki/Q515701","display_name":"Linked data","level":3,"score":0.3188000023365021},{"id":"https://openalex.org/C151719136","wikidata":"https://www.wikidata.org/wiki/Q3972943","display_name":"Publishing","level":2,"score":0.31369999051094055},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.3037000000476837},{"id":"https://openalex.org/C39896193","wikidata":"https://www.wikidata.org/wiki/Q380344","display_name":"Descriptive statistics","level":2,"score":0.27970001101493835},{"id":"https://openalex.org/C67186912","wikidata":"https://www.wikidata.org/wiki/Q367664","display_name":"Data modeling","level":2,"score":0.2712000012397766},{"id":"https://openalex.org/C171686336","wikidata":"https://www.wikidata.org/wiki/Q3532085","display_name":"Topic model","level":2,"score":0.2583000063896179}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2606.02334","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2606.02334","pdf_url":null,"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":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"doi:10.48550/arxiv.2606.02334","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2606.02334","pdf_url":null,"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":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"},"sustainable_development_goals":[{"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4","score":0.46842193603515625}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Dataset":[0],"search":[1],"and":[2,44,63,89,100,102,106,109,117],"reuse":[3],"are":[4,18],"strongly":[5],"constrained":[6],"by":[7],"the":[8,75],"quality":[9,62,126],"of":[10,59],"metadata":[11],"such":[12,30],"as":[13],"natural":[14],"language":[15,25],"descriptions,":[16],"which":[17],"often":[19,138],"sparse":[20],"or":[21],"inconsistent.":[22],"Although":[23],"large":[24],"models":[26],"(LLMs)":[27],"can":[28],"generate":[29,81],"descriptions":[31,82],"automatically,":[32],"little":[33],"empirical":[34],"guidance":[35,167],"exists":[36],"on":[37],"what":[38,45],"makes":[39],"a":[40,56,64,86,118,131],"good":[41],"dataset":[42,46,60,96],"description":[43,61],"context":[47],"LLMs":[48,84,158],"actually":[49],"need.":[50],"We":[51,80,153],"study":[52,67],"these":[53],"questions":[54],"through":[55],"literature-grounded":[57],"framework":[58,116],"large-scale":[65],"ablation":[66,91],"using":[68,94],"252":[69],"datasets":[70],"(1,336":[71],"CSV":[72],"files)":[73],"from":[74],"European":[76],"data":[77,144,170],"portal":[78],"data.europa.eu.":[79],"with":[83,112],"in":[85,124],"baseline":[87],"scenario":[88],"two":[90],"scenarios:":[92],"(1)":[93],"only":[95],"titles,":[97,104],"(2)":[98],"titles":[99],"schema,":[101],"(3)":[103],"schema":[105,134],"representative":[107,143],"data,":[108],"evaluate":[110],"them":[111],"an":[113],"LLM-as-a-":[114],"judge":[115],"semantic":[119],"descriptive":[120,161],"attribute":[121],"analysis":[122],"grounded":[123],"our":[125],"dimensions.":[127],"Our":[128],"results":[129],"reveal":[130],"consis-":[132],"tent":[133],"penalty:":[135],"table-schemas":[136],"alone":[137],"degrade":[139],"narrative":[140],"quality,":[141],"while":[142],"partially":[145],"restores":[146],"grounding":[147],"without":[148],"improving":[149],"overall":[150],"human-facing":[151],"quality.":[152],"further":[154],"show":[155],"that":[156],"different":[157],"exhibit":[159],"stable":[160],"personas.":[162],"These":[163],"findings":[164],"provide":[165],"practical":[166],"for":[168],"LLM-supported":[169],"publishing":[171],"workflows.":[172]},"counts_by_year":[],"updated_date":"2026-07-01T06:00:48.157686","created_date":"2026-06-03T00:00:00"}