{"id":"https://openalex.org/W4416075225","doi":"https://doi.org/10.48550/arxiv.2506.04172","title":"Does Prompt Design Impact Quality of Data Imputation by LLMs?","display_name":"Does Prompt Design Impact Quality of Data Imputation by LLMs?","publication_year":2025,"publication_date":"2025-06-04","ids":{"openalex":"https://openalex.org/W4416075225","doi":"https://doi.org/10.48550/arxiv.2506.04172"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2506.04172","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2506.04172","pdf_url":"https://arxiv.org/pdf/2506.04172","source":{"id":"https://openalex.org/S4393918464","display_name":"ArXiv.org","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"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"},"type":"preprint","indexed_in":["arxiv","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2506.04172","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5020147598","display_name":"Sachin Srinivasan","orcid":"https://orcid.org/0000-0002-2250-5347"},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Srinivasan, Shreenidhi","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5024292585","display_name":"Lydia Manikonda","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Manikonda, Lydia","raw_affiliation_strings":[],"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5020147598"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"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/T11652","display_name":"Imbalanced Data Classification Techniques","score":0.4977000057697296,"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/T11652","display_name":"Imbalanced Data Classification Techniques","score":0.4977000057697296,"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/T12072","display_name":"Machine Learning and Algorithms","score":0.1574999988079071,"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/T12535","display_name":"Machine Learning and Data Classification","score":0.10530000180006027,"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/imputation","display_name":"Imputation (statistics)","score":0.857200026512146},{"id":"https://openalex.org/keywords/data-quality","display_name":"Data quality","score":0.5834000110626221},{"id":"https://openalex.org/keywords/missing-data","display_name":"Missing data","score":0.5584999918937683},{"id":"https://openalex.org/keywords/binary-number","display_name":"Binary number","score":0.3467000126838684},{"id":"https://openalex.org/keywords/baseline","display_name":"Baseline (sea)","score":0.3391000032424927},{"id":"https://openalex.org/keywords/training-set","display_name":"Training set","score":0.3310000002384186}],"concepts":[{"id":"https://openalex.org/C58041806","wikidata":"https://www.wikidata.org/wiki/Q1660484","display_name":"Imputation (statistics)","level":3,"score":0.857200026512146},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7544000148773193},{"id":"https://openalex.org/C24756922","wikidata":"https://www.wikidata.org/wiki/Q1757694","display_name":"Data quality","level":3,"score":0.5834000110626221},{"id":"https://openalex.org/C9357733","wikidata":"https://www.wikidata.org/wiki/Q6878417","display_name":"Missing data","level":2,"score":0.5584999918937683},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.5497000217437744},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4758000075817108},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4065000116825104},{"id":"https://openalex.org/C48372109","wikidata":"https://www.wikidata.org/wiki/Q3913","display_name":"Binary number","level":2,"score":0.3467000126838684},{"id":"https://openalex.org/C12725497","wikidata":"https://www.wikidata.org/wiki/Q810247","display_name":"Baseline (sea)","level":2,"score":0.3391000032424927},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.3310000002384186},{"id":"https://openalex.org/C160920958","wikidata":"https://www.wikidata.org/wiki/Q7662746","display_name":"Synthetic data","level":2,"score":0.3264000117778778},{"id":"https://openalex.org/C67186912","wikidata":"https://www.wikidata.org/wiki/Q367664","display_name":"Data modeling","level":2,"score":0.29750001430511475},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.2833999991416931},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.2694000005722046},{"id":"https://openalex.org/C3020493868","wikidata":"https://www.wikidata.org/wiki/Q55631277","display_name":"Real world data","level":2,"score":0.2533000111579895},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.2524999976158142}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2506.04172","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2506.04172","pdf_url":"https://arxiv.org/pdf/2506.04172","source":{"id":"https://openalex.org/S4393918464","display_name":"ArXiv.org","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"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"},{"id":"doi:10.48550/arxiv.2506.04172","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2506.04172","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":"article"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2506.04172","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2506.04172","pdf_url":"https://arxiv.org/pdf/2506.04172","source":{"id":"https://openalex.org/S4393918464","display_name":"ArXiv.org","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"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":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4416075225.pdf","grobid_xml":"https://content.openalex.org/works/W4416075225.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Generating":[0],"realistic":[1],"synthetic":[2,145,196],"tabular":[3],"data":[4,20,31,146,157,164,197],"presents":[5,27],"a":[6,28,51,152,167],"critical":[7,153],"challenge":[8],"in":[9,64,120,155],"machine":[10],"learning.":[11],"It":[12],"adds":[13],"another":[14],"layer":[15],"of":[16,40,50,60,82,117,124,138,189],"complexity":[17],"when":[18,141],"this":[19,70,125],"contain":[21],"class":[22],"imbalance":[23],"problems.":[24],"This":[25,44],"paper":[26],"novel":[29],"token-aware":[30],"imputation":[32,83,105,158],"method":[33],"that":[34,92,115,175],"leverages":[35],"the":[36,48,58,65,80,97,136,186],"in-context":[37],"learning":[38],"capabilities":[39],"large":[41],"language":[42],"models.":[43],"is":[45,128],"achieved":[46],"through":[47],"combination":[49],"structured":[52],"group-wise":[53],"CSV-style":[54],"prompting":[55],"technique":[56],"and":[57,78,148,182,191],"elimination":[59],"irrelevant":[61],"contextual":[62],"information":[63],"input":[66,98],"prompt.":[67],"We":[68,173],"test":[69],"approach":[71,94],"with":[72,162],"two":[73],"class-imbalanced":[74,160],"binary":[75],"classification":[76],"datasets":[77,114,161],"evaluate":[79],"effectiveness":[81],"using":[84],"classification-based":[85],"evaluation":[86],"metrics.":[87],"The":[88,122],"experimental":[89],"results":[90],"demonstrate":[91],"our":[93,109,176],"significantly":[95],"reduces":[96],"prompt":[99,139,192],"size":[100],"while":[101],"maintaining":[102],"or":[103],"improving":[104],"quality":[106],"compared":[107],"to":[108],"baseline":[110],"prompt,":[111],"especially":[112],"for":[113,144,159,195],"are":[116],"relatively":[118],"smaller":[119],"size.":[121],"contributions":[123],"presented":[126],"work":[127,177],"two-fold":[129],"--":[130],"1)":[131],"it":[132,150],"sheds":[133],"light":[134],"on":[135],"importance":[137],"design":[140],"leveraging":[142,185],"LLMs":[143,190],"generation":[147],"2)":[149],"addresses":[151],"gap":[154],"LLM-based":[156],"missing":[163],"by":[165],"providing":[166],"practical":[168],"solution":[169],"within":[170],"computational":[171],"constraints.":[172],"hope":[174],"will":[178],"foster":[179],"further":[180],"research":[181],"discussions":[183],"about":[184],"incredible":[187],"potential":[188],"engineering":[193],"techniques":[194],"generation.":[198]},"counts_by_year":[],"updated_date":"2026-03-10T16:38:18.471706","created_date":"2025-10-10T00:00:00"}