{"id":"https://openalex.org/W4396831698","doi":"https://doi.org/10.1145/3613905.3651115","title":"Leveraging Large Language Models to Enhance Domain Expert Inclusion in Data Science Workflows","display_name":"Leveraging Large Language Models to Enhance Domain Expert Inclusion in Data Science Workflows","publication_year":2024,"publication_date":"2024-05-02","ids":{"openalex":"https://openalex.org/W4396831698","doi":"https://doi.org/10.1145/3613905.3651115"},"language":"en","primary_location":{"id":"doi:10.1145/3613905.3651115","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3613905.3651115","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3613905.3651115","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Extended Abstracts of the CHI Conference on Human Factors in Computing Systems","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://dl.acm.org/doi/pdf/10.1145/3613905.3651115","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5097223149","display_name":"Jasmine Y. Shih","orcid":"https://orcid.org/0009-0005-9568-6934"},"institutions":[{"id":"https://openalex.org/I97018004","display_name":"Stanford University","ror":"https://ror.org/00f54p054","country_code":"US","type":"education","lineage":["https://openalex.org/I97018004"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Jasmine Y Shih","raw_affiliation_strings":["Computer Science, Stanford University, United States"],"raw_orcid":"https://orcid.org/0009-0005-9568-6934","affiliations":[{"raw_affiliation_string":"Computer Science, Stanford University, United States","institution_ids":["https://openalex.org/I97018004"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5033867256","display_name":"Vishal Mohanty","orcid":"https://orcid.org/0000-0002-1556-1113"},"institutions":[{"id":"https://openalex.org/I97018004","display_name":"Stanford University","ror":"https://ror.org/00f54p054","country_code":"US","type":"education","lineage":["https://openalex.org/I97018004"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Vishal Mohanty","raw_affiliation_strings":["Computer Science, Stanford University, United States"],"raw_orcid":"https://orcid.org/0000-0002-1556-1113","affiliations":[{"raw_affiliation_string":"Computer Science, Stanford University, United States","institution_ids":["https://openalex.org/I97018004"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5006509575","display_name":"Yannis Katsis","orcid":"https://orcid.org/0000-0002-1733-6227"},"institutions":[{"id":"https://openalex.org/I4210085935","display_name":"IBM Research - Almaden","ror":"https://ror.org/005w8dd04","country_code":"US","type":"facility","lineage":["https://openalex.org/I1341412227","https://openalex.org/I4210085935","https://openalex.org/I4210114115"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yannis Katsis","raw_affiliation_strings":["IBM Research, Almaden, United States"],"raw_orcid":"https://orcid.org/0000-0002-1733-6227","affiliations":[{"raw_affiliation_string":"IBM Research, Almaden, United States","institution_ids":["https://openalex.org/I4210085935"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5072561188","display_name":"Hari Subramonyam","orcid":"https://orcid.org/0000-0002-3450-0447"},"institutions":[{"id":"https://openalex.org/I97018004","display_name":"Stanford University","ror":"https://ror.org/00f54p054","country_code":"US","type":"education","lineage":["https://openalex.org/I97018004"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Hari Subramonyam","raw_affiliation_strings":["Stanford University, United States"],"raw_orcid":"https://orcid.org/0000-0002-3450-0447","affiliations":[{"raw_affiliation_string":"Stanford University, United States","institution_ids":["https://openalex.org/I97018004"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5097223149"],"corresponding_institution_ids":["https://openalex.org/I97018004"],"apc_list":null,"apc_paid":null,"fwci":2.9688,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":{"value":0.92669236,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"11"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11986","display_name":"Scientific Computing and Data Management","score":0.998199999332428,"subfield":{"id":"https://openalex.org/subfields/1802","display_name":"Information Systems and Management"},"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/T11986","display_name":"Scientific Computing and Data Management","score":0.998199999332428,"subfield":{"id":"https://openalex.org/subfields/1802","display_name":"Information Systems and Management"},"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/T12026","display_name":"Explainable Artificial Intelligence (XAI)","score":0.9933000206947327,"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/T10883","display_name":"Ethics and Social Impacts of AI","score":0.9886999726295471,"subfield":{"id":"https://openalex.org/subfields/3311","display_name":"Safety Research"},"field":{"id":"https://openalex.org/fields/33","display_name":"Social Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8457392454147339},{"id":"https://openalex.org/keywords/workflow","display_name":"Workflow","score":0.7517716884613037},{"id":"https://openalex.org/keywords/documentation","display_name":"Documentation","score":0.657987117767334},{"id":"https://openalex.org/keywords/domain","display_name":"Domain (mathematical analysis)","score":0.6507722735404968},{"id":"https://openalex.org/keywords/visualization","display_name":"Visualization","score":0.6322586536407471},{"id":"https://openalex.org/keywords/data-science","display_name":"Data science","score":0.6001718640327454},{"id":"https://openalex.org/keywords/relevance","display_name":"Relevance (law)","score":0.5449517965316772},{"id":"https://openalex.org/keywords/dashboard","display_name":"Dashboard","score":0.4953433573246002},{"id":"https://openalex.org/keywords/visibility","display_name":"Visibility","score":0.4663514196872711},{"id":"https://openalex.org/keywords/data-modeling","display_name":"Data modeling","score":0.42413920164108276},{"id":"https://openalex.org/keywords/data-visualization","display_name":"Data visualization","score":0.4237465262413025},{"id":"https://openalex.org/keywords/transparency","display_name":"Transparency (behavior)","score":0.41802510619163513},{"id":"https://openalex.org/keywords/domain-specific-language","display_name":"Domain-specific language","score":0.41143783926963806},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.34329938888549805},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.34112322330474854},{"id":"https://openalex.org/keywords/software-engineering","display_name":"Software engineering","score":0.3296140134334564},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.23800253868103027},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.20478275418281555},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.17622312903404236}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8457392454147339},{"id":"https://openalex.org/C177212765","wikidata":"https://www.wikidata.org/wiki/Q627335","display_name":"Workflow","level":2,"score":0.7517716884613037},{"id":"https://openalex.org/C56666940","wikidata":"https://www.wikidata.org/wiki/Q788790","display_name":"Documentation","level":2,"score":0.657987117767334},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.6507722735404968},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.6322586536407471},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.6001718640327454},{"id":"https://openalex.org/C158154518","wikidata":"https://www.wikidata.org/wiki/Q7310970","display_name":"Relevance (law)","level":2,"score":0.5449517965316772},{"id":"https://openalex.org/C33499554","wikidata":"https://www.wikidata.org/wiki/Q1417134","display_name":"Dashboard","level":2,"score":0.4953433573246002},{"id":"https://openalex.org/C123403432","wikidata":"https://www.wikidata.org/wiki/Q654068","display_name":"Visibility","level":2,"score":0.4663514196872711},{"id":"https://openalex.org/C67186912","wikidata":"https://www.wikidata.org/wiki/Q367664","display_name":"Data modeling","level":2,"score":0.42413920164108276},{"id":"https://openalex.org/C172367668","wikidata":"https://www.wikidata.org/wiki/Q6504956","display_name":"Data visualization","level":3,"score":0.4237465262413025},{"id":"https://openalex.org/C2780233690","wikidata":"https://www.wikidata.org/wiki/Q535347","display_name":"Transparency (behavior)","level":2,"score":0.41802510619163513},{"id":"https://openalex.org/C135257023","wikidata":"https://www.wikidata.org/wiki/Q691358","display_name":"Domain-specific language","level":2,"score":0.41143783926963806},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.34329938888549805},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.34112322330474854},{"id":"https://openalex.org/C115903868","wikidata":"https://www.wikidata.org/wiki/Q80993","display_name":"Software engineering","level":1,"score":0.3296140134334564},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.23800253868103027},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.20478275418281555},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.17622312903404236},{"id":"https://openalex.org/C120665830","wikidata":"https://www.wikidata.org/wiki/Q14620","display_name":"Optics","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.0},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.0},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3613905.3651115","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3613905.3651115","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3613905.3651115","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Extended Abstracts of the CHI Conference on Human Factors in Computing Systems","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3613905.3651115","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3613905.3651115","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3613905.3651115","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Extended Abstracts of the CHI Conference on Human Factors in Computing Systems","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":false},"content_urls":{"pdf":"https://content.openalex.org/works/W4396831698.pdf"},"referenced_works_count":46,"referenced_works":["https://openalex.org/W2017670237","https://openalex.org/W2039570985","https://openalex.org/W2152225808","https://openalex.org/W2753739212","https://openalex.org/W2888109941","https://openalex.org/W2897042519","https://openalex.org/W2912299932","https://openalex.org/W2915273119","https://openalex.org/W2939783009","https://openalex.org/W2965211237","https://openalex.org/W2971867419","https://openalex.org/W2974071289","https://openalex.org/W2981869278","https://openalex.org/W2983901715","https://openalex.org/W3029838198","https://openalex.org/W3032086959","https://openalex.org/W3091952951","https://openalex.org/W3092479831","https://openalex.org/W3100279624","https://openalex.org/W3118813946","https://openalex.org/W3121784008","https://openalex.org/W3125798375","https://openalex.org/W3152762006","https://openalex.org/W3157506384","https://openalex.org/W3197347140","https://openalex.org/W3199384803","https://openalex.org/W3212368439","https://openalex.org/W3214911045","https://openalex.org/W4220718380","https://openalex.org/W4221143046","https://openalex.org/W4224991249","https://openalex.org/W4225492311","https://openalex.org/W4282813546","https://openalex.org/W4282933047","https://openalex.org/W4283770708","https://openalex.org/W4284670548","https://openalex.org/W4288083705","https://openalex.org/W4294559022","https://openalex.org/W4308784155","https://openalex.org/W4313433600","https://openalex.org/W4313547549","https://openalex.org/W4366548004","https://openalex.org/W4380361082","https://openalex.org/W4381738044","https://openalex.org/W4388448486","https://openalex.org/W4402860127"],"related_works":["https://openalex.org/W2392812199","https://openalex.org/W4200176076","https://openalex.org/W598185802","https://openalex.org/W2607236244","https://openalex.org/W2355516524","https://openalex.org/W2361471170","https://openalex.org/W2810922655","https://openalex.org/W4367333247","https://openalex.org/W2147224006","https://openalex.org/W4387885925"],"abstract_inverted_index":{"Domain":[0],"experts":[1,104],"can":[2,105],"play":[3],"a":[4,60,65,80],"crucial":[5],"role":[6],"in":[7,24],"guiding":[8],"data":[9,110,116,128,148],"scientists":[10],"to":[11,32,73,92,127],"optimize":[12],"machine":[13],"learning":[14],"models":[15],"while":[16],"ensuring":[17],"contextual":[18],"relevance":[19],"for":[20],"downstream":[21],"use.":[22],"However,":[23],"current":[25],"workflows,":[26],"such":[27],"collaboration":[28,61],"is":[29],"challenging":[30],"due":[31],"differing":[33],"expertise,":[34],"abstract":[35],"documentation":[36],"practices,":[37],"and":[38,42,52,75,78,111,124,138,145],"lack":[39],"of":[40,147],"access":[41],"visibility":[43],"into":[44],"low-level":[45],"implementation":[46],"artifacts.":[47],"To":[48],"address":[49],"these":[50],"challenges":[51],"enable":[53,121],"domain":[54,93,103],"expert":[55],"participation,":[56],"we":[57],"introduce":[58],"CellSync,":[59],"framework":[62],"comprising":[63],"(1)":[64],"Jupyter":[66],"Notebook":[67],"extension":[68],"that":[69,87,134],"continuously":[70],"tracks":[71],"changes":[72,90],"dataframes":[74],"model":[76],"metrics":[77],"(2)":[79],"Large":[81],"Language":[82],"Model":[83],"powered":[84],"visualization":[85,99],"dashboard":[86],"makes":[88],"those":[89],"interpretable":[91],"experts.":[94],"Through":[95],"CellSync\u2019s":[96],"cell-level":[97],"dataset":[98],"with":[100],"code":[101],"summaries,":[102],"interactively":[106],"examine":[107],"how":[108],"individual":[109],"modeling":[112],"operations":[113],"impact":[114],"different":[115],"segments.":[117],"The":[118],"chat":[119],"features":[120],"data-centric":[122],"conversations":[123],"targeted":[125],"feedback":[126],"scientists.":[129],"Our":[130],"preliminary":[131],"evaluation":[132],"shows":[133],"CellSync":[135],"provides":[136],"transparency":[137],"promotes":[139],"critical":[140],"discussions":[141],"about":[142],"the":[143],"intents":[144],"implications":[146],"operations.":[149]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}