{"id":"https://openalex.org/W7128480797","doi":"https://doi.org/10.1145/3772318.3791222","title":"Data-Prompt Co-Evolution: Growing Test Sets to Refine LLM Behavior","display_name":"Data-Prompt Co-Evolution: Growing Test Sets to Refine LLM Behavior","publication_year":2026,"publication_date":"2026-04-13","ids":{"openalex":"https://openalex.org/W7128480797","doi":"https://doi.org/10.1145/3772318.3791222"},"language":null,"primary_location":{"id":"doi:10.1145/3772318.3791222","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3772318.3791222","pdf_url":null,"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 2026 CHI Conference on Human Factors in Computing Systems","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.1145/3772318.3791222","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5125520461","display_name":"Minjae Lee","orcid":null},"institutions":[{"id":"https://openalex.org/I193775966","display_name":"Yonsei University","ror":"https://ror.org/01wjejq96","country_code":"KR","type":"education","lineage":["https://openalex.org/I193775966"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Minjae Lee","raw_affiliation_strings":["Department of Computer Science and Engineering, Yonsei University, Seoul, Republic of Korea"],"raw_orcid":"https://orcid.org/0009-0000-0232-7486","affiliations":[{"raw_affiliation_string":"Department of Computer Science and Engineering, Yonsei University, Seoul, Republic of Korea","institution_ids":["https://openalex.org/I193775966"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5042350842","display_name":"Minsuk Kahng","orcid":"https://orcid.org/0000-0002-0291-6026"},"institutions":[{"id":"https://openalex.org/I193775966","display_name":"Yonsei University","ror":"https://ror.org/01wjejq96","country_code":"KR","type":"education","lineage":["https://openalex.org/I193775966"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Minsuk Kahng","raw_affiliation_strings":["Department of Computer Science and Engineering, Yonsei University, Seoul, Republic of Korea"],"raw_orcid":"https://orcid.org/0000-0002-0291-6026","affiliations":[{"raw_affiliation_string":"Department of Computer Science and Engineering, Yonsei University, Seoul, Republic of Korea","institution_ids":["https://openalex.org/I193775966"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I193775966"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":true,"cited_by_count":1,"citation_normalized_percentile":{"value":0.11812808,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"17"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.28200000524520874,"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":0.28200000524520874,"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/T13910","display_name":"Computational and Text Analysis Methods","score":0.06800000369548798,"subfield":{"id":"https://openalex.org/subfields/3300","display_name":"General Social Sciences"},"field":{"id":"https://openalex.org/fields/33","display_name":"Social Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T11636","display_name":"Artificial Intelligence in Healthcare and Education","score":0.06310000270605087,"subfield":{"id":"https://openalex.org/subfields/2718","display_name":"Health Informatics"},"field":{"id":"https://openalex.org/fields/27","display_name":"Medicine"},"domain":{"id":"https://openalex.org/domains/4","display_name":"Health Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/test","display_name":"Test (biology)","score":0.660099983215332},{"id":"https://openalex.org/keywords/workflow","display_name":"Workflow","score":0.6398000121116638},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.6208000183105469},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.605400025844574},{"id":"https://openalex.org/keywords/iterative-and-incremental-development","display_name":"Iterative and incremental development","score":0.5109000205993652},{"id":"https://openalex.org/keywords/encoding","display_name":"Encoding (memory)","score":0.40619999170303345},{"id":"https://openalex.org/keywords/test-set","display_name":"Test set","score":0.4002000093460083},{"id":"https://openalex.org/keywords/enhanced-data-rates-for-gsm-evolution","display_name":"Enhanced Data Rates for GSM Evolution","score":0.37439998984336853}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7157999873161316},{"id":"https://openalex.org/C2777267654","wikidata":"https://www.wikidata.org/wiki/Q3519023","display_name":"Test (biology)","level":2,"score":0.660099983215332},{"id":"https://openalex.org/C177212765","wikidata":"https://www.wikidata.org/wiki/Q627335","display_name":"Workflow","level":2,"score":0.6398000121116638},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.6208000183105469},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.605400025844574},{"id":"https://openalex.org/C143587482","wikidata":"https://www.wikidata.org/wiki/Q1543216","display_name":"Iterative and incremental development","level":2,"score":0.5109000205993652},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.44179999828338623},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.41830000281333923},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.4146000146865845},{"id":"https://openalex.org/C125411270","wikidata":"https://www.wikidata.org/wiki/Q18653","display_name":"Encoding (memory)","level":2,"score":0.40619999170303345},{"id":"https://openalex.org/C169903167","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Test set","level":2,"score":0.4002000093460083},{"id":"https://openalex.org/C162307627","wikidata":"https://www.wikidata.org/wiki/Q204833","display_name":"Enhanced Data Rates for GSM Evolution","level":2,"score":0.37439998984336853},{"id":"https://openalex.org/C128942645","wikidata":"https://www.wikidata.org/wiki/Q1568346","display_name":"Test case","level":3,"score":0.33219999074935913},{"id":"https://openalex.org/C115903868","wikidata":"https://www.wikidata.org/wiki/Q80993","display_name":"Software engineering","level":1,"score":0.3125999867916107},{"id":"https://openalex.org/C16910744","wikidata":"https://www.wikidata.org/wiki/Q7705759","display_name":"Test data","level":2,"score":0.31200000643730164},{"id":"https://openalex.org/C18762648","wikidata":"https://www.wikidata.org/wiki/Q42213","display_name":"Work (physics)","level":2,"score":0.29420000314712524},{"id":"https://openalex.org/C165825675","wikidata":"https://www.wikidata.org/wiki/Q1399743","display_name":"Model-based testing","level":4,"score":0.2913999855518341},{"id":"https://openalex.org/C80519477","wikidata":"https://www.wikidata.org/wiki/Q3532236","display_name":"Scenario testing","level":3,"score":0.29019999504089355},{"id":"https://openalex.org/C2779982483","wikidata":"https://www.wikidata.org/wiki/Q6094420","display_name":"Iterative refinement","level":2,"score":0.289000004529953},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.2775999903678894},{"id":"https://openalex.org/C58489278","wikidata":"https://www.wikidata.org/wiki/Q1172284","display_name":"Data set","level":2,"score":0.2524000108242035}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/3772318.3791222","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3772318.3791222","pdf_url":null,"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 2026 CHI Conference on Human Factors in Computing Systems","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2510.12728","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2510.12728","pdf_url":"https://arxiv.org/pdf/2510.12728","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"}],"best_oa_location":{"id":"doi:10.1145/3772318.3791222","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3772318.3791222","pdf_url":null,"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 2026 CHI Conference on Human Factors in Computing Systems","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Large":[0],"Language":[1],"Models":[2],"(LLMs)":[3],"are":[4,42],"increasingly":[5],"embedded":[6],"in":[7,53,95],"applications,":[8],"and":[9,39,59,79,91,119,153],"people":[10,136],"can":[11],"shape":[12],"model":[13,55],"behavior":[14],"by":[15],"editing":[16],"prompt":[17,40,72,92],"instructions.":[18],"Yet":[19],"encoding":[20],"subtle,":[21],"domain-specific":[22],"policies":[23],"into":[24],"prompts":[25,123,138],"is":[26],"challenging.":[27],"Although":[28],"this":[29,77,104],"process":[30],"often":[31],"benefits":[32],"from":[33],"concrete":[34],"test":[35,37,60,89,127],"cases,":[36,113],"data":[38],"instructions":[41,93],"typically":[43],"developed":[44],"as":[45],"separate":[46],"artifacts,":[47],"reflecting":[48],"traditional":[49],"machine":[50],"learning":[51],"practices":[52],"which":[54],"tuning":[56],"was":[57],"slow":[58],"sets":[61],"were":[62],"static.":[63],"We":[64,97],"argue":[65],"that":[66,102],"the":[67],"fast,":[68],"iterative":[69],"nature":[70],"of":[71],"engineering":[73],"calls":[74],"for":[75,116],"removing":[76],"separation":[78],"enabling":[80],"a":[81,87,125],"new":[82],"workflow:":[83],"data-prompt":[84],"co-evolution,":[85],"where":[86],"living":[88],"set":[90],"evolve":[94],"tandem.":[96],"present":[98],"an":[99],"interactive":[100],"system":[101],"operationalizes":[103],"workflow.":[105],"It":[106],"guides":[107],"application":[108],"developers":[109],"to":[110],"discover":[111],"edge":[112],"articulate":[114],"rationales":[115],"desired":[117],"behavior,":[118],"iteratively":[120],"evaluate":[121],"revised":[122],"against":[124],"growing":[126],"set.":[128],"A":[129],"user":[130],"study":[131],"shows":[132],"our":[133],"workflow":[134],"helps":[135],"refine":[137],"systematically,":[139],"better":[140],"aligning":[141],"them":[142],"with":[143],"their":[144],"intended":[145],"policies.":[146],"This":[147],"work":[148],"points":[149],"toward":[150],"more":[151],"robust":[152],"responsible":[154],"LLM":[155],"applications":[156],"through":[157],"human-in-the-loop":[158],"development.":[159]},"counts_by_year":[],"updated_date":"2026-08-18T07:49:30.821534","created_date":"2026-02-11T00:00:00"}