{"id":"https://openalex.org/W4399213744","doi":"https://doi.org/10.1145/3639477.3639720","title":"Assessing LLMs for High Stakes Applications","display_name":"Assessing LLMs for High Stakes Applications","publication_year":2024,"publication_date":"2024-04-14","ids":{"openalex":"https://openalex.org/W4399213744","doi":"https://doi.org/10.1145/3639477.3639720"},"language":"en","primary_location":{"id":"doi:10.1145/3639477.3639720","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3639477.3639720","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3639477.3639720","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 46th International Conference on Software Engineering: Software Engineering in Practice","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/10.1145/3639477.3639720","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5037586166","display_name":"Shannon Gallagher","orcid":"https://orcid.org/0000-0003-1114-3851"},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]},{"id":"https://openalex.org/I114772536","display_name":"Software Engineering Institute","ror":"https://ror.org/01xqjjn94","country_code":"US","type":"facility","lineage":["https://openalex.org/I114772536","https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Shannon K. Gallagher","raw_affiliation_strings":["Software Engineering Institute, Carnegie Mellon University, Pittsburgh, Pennsylvania, USA"],"affiliations":[{"raw_affiliation_string":"Software Engineering Institute, Carnegie Mellon University, Pittsburgh, Pennsylvania, USA","institution_ids":["https://openalex.org/I114772536","https://openalex.org/I74973139"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5052102516","display_name":"J. Ratchford","orcid":"https://orcid.org/0009-0007-1898-8415"},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]},{"id":"https://openalex.org/I114772536","display_name":"Software Engineering Institute","ror":"https://ror.org/01xqjjn94","country_code":"US","type":"facility","lineage":["https://openalex.org/I114772536","https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jasmine Ratchford","raw_affiliation_strings":["Software Engineering Institute, Carnegie Mellon University, Pittsburgh, Pennsylvania, USA"],"affiliations":[{"raw_affiliation_string":"Software Engineering Institute, Carnegie Mellon University, Pittsburgh, Pennsylvania, USA","institution_ids":["https://openalex.org/I114772536","https://openalex.org/I74973139"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5098959776","display_name":"Tyler Brooks","orcid":"https://orcid.org/0009-0005-3266-1895"},"institutions":[{"id":"https://openalex.org/I114772536","display_name":"Software Engineering Institute","ror":"https://ror.org/01xqjjn94","country_code":"US","type":"facility","lineage":["https://openalex.org/I114772536","https://openalex.org/I74973139"]},{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Tyler Brooks","raw_affiliation_strings":["Software Engineering Institute, Carnegie Mellon University, Pittsburgh, Pennsylvania, USA"],"affiliations":[{"raw_affiliation_string":"Software Engineering Institute, Carnegie Mellon University, Pittsburgh, Pennsylvania, USA","institution_ids":["https://openalex.org/I114772536","https://openalex.org/I74973139"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5105975475","display_name":"Bryan P. Brown","orcid":"https://orcid.org/0009-0005-9372-0246"},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]},{"id":"https://openalex.org/I114772536","display_name":"Software Engineering Institute","ror":"https://ror.org/01xqjjn94","country_code":"US","type":"facility","lineage":["https://openalex.org/I114772536","https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Bryan P. Brown","raw_affiliation_strings":["Software Engineering Institute, Carnegie Mellon University, Pittsburgh, Pennsylvania, USA"],"affiliations":[{"raw_affiliation_string":"Software Engineering Institute, Carnegie Mellon University, Pittsburgh, Pennsylvania, USA","institution_ids":["https://openalex.org/I114772536","https://openalex.org/I74973139"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103060302","display_name":"Eric Heim","orcid":"https://orcid.org/0009-0003-5544-3204"},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]},{"id":"https://openalex.org/I114772536","display_name":"Software Engineering Institute","ror":"https://ror.org/01xqjjn94","country_code":"US","type":"facility","lineage":["https://openalex.org/I114772536","https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Eric Heim","raw_affiliation_strings":["Software Engineering Institute, Carnegie Mellon University, Pittsburgh, Pennsylvania, USA"],"affiliations":[{"raw_affiliation_string":"Software Engineering Institute, Carnegie Mellon University, Pittsburgh, Pennsylvania, USA","institution_ids":["https://openalex.org/I114772536","https://openalex.org/I74973139"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103143311","display_name":"William Nichols","orcid":"https://orcid.org/0009-0007-2198-8918"},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]},{"id":"https://openalex.org/I114772536","display_name":"Software Engineering Institute","ror":"https://ror.org/01xqjjn94","country_code":"US","type":"facility","lineage":["https://openalex.org/I114772536","https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"William R. Nichols","raw_affiliation_strings":["Software Engineering Institute, Carnegie Mellon University, Pittsburgh, Pennsylvania, USA"],"affiliations":[{"raw_affiliation_string":"Software Engineering Institute, Carnegie Mellon University, Pittsburgh, Pennsylvania, USA","institution_ids":["https://openalex.org/I114772536","https://openalex.org/I74973139"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5028007059","display_name":"Scott McMillan","orcid":"https://orcid.org/0000-0003-1868-5178"},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]},{"id":"https://openalex.org/I114772536","display_name":"Software Engineering Institute","ror":"https://ror.org/01xqjjn94","country_code":"US","type":"facility","lineage":["https://openalex.org/I114772536","https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Scott Mcmillan","raw_affiliation_strings":["Software Engineering Institute, Carnegie Mellon University, Pittsburgh, Pennsylvania, USA"],"affiliations":[{"raw_affiliation_string":"Software Engineering Institute, Carnegie Mellon University, Pittsburgh, Pennsylvania, USA","institution_ids":["https://openalex.org/I114772536","https://openalex.org/I74973139"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5087926682","display_name":"Swati Rallapalli","orcid":"https://orcid.org/0000-0003-2528-5316"},"institutions":[{"id":"https://openalex.org/I114772536","display_name":"Software Engineering Institute","ror":"https://ror.org/01xqjjn94","country_code":"US","type":"facility","lineage":["https://openalex.org/I114772536","https://openalex.org/I74973139"]},{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Swati Rallapalli","raw_affiliation_strings":["Software Engineering Institute, Carnegie Mellon University, Pittsburgh, Pennsylvania, USA"],"affiliations":[{"raw_affiliation_string":"Software Engineering Institute, Carnegie Mellon University, Pittsburgh, Pennsylvania, USA","institution_ids":["https://openalex.org/I114772536","https://openalex.org/I74973139"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5016806880","display_name":"Carol J. Smith","orcid":"https://orcid.org/0000-0003-0087-3736"},"institutions":[{"id":"https://openalex.org/I114772536","display_name":"Software Engineering Institute","ror":"https://ror.org/01xqjjn94","country_code":"US","type":"facility","lineage":["https://openalex.org/I114772536","https://openalex.org/I74973139"]},{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Carol J. Smith","raw_affiliation_strings":["Software Engineering Institute, Carnegie Mellon University, Pittsburgh, Pennsylvania, USA"],"affiliations":[{"raw_affiliation_string":"Software Engineering Institute, Carnegie Mellon University, Pittsburgh, Pennsylvania, USA","institution_ids":["https://openalex.org/I114772536","https://openalex.org/I74973139"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5037987745","display_name":"Nathan VanHoudnos","orcid":"https://orcid.org/0000-0001-8047-3091"},"institutions":[{"id":"https://openalex.org/I114772536","display_name":"Software Engineering Institute","ror":"https://ror.org/01xqjjn94","country_code":"US","type":"facility","lineage":["https://openalex.org/I114772536","https://openalex.org/I74973139"]},{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Nathan Vanhoudnos","raw_affiliation_strings":["Software Engineering Institute, Carnegie Mellon University, Pittsburgh, Pennsylvania, USA"],"affiliations":[{"raw_affiliation_string":"Software Engineering Institute, Carnegie Mellon University, Pittsburgh, Pennsylvania, USA","institution_ids":["https://openalex.org/I114772536","https://openalex.org/I74973139"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5098959774","display_name":"Nick Winski","orcid":null},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]},{"id":"https://openalex.org/I114772536","display_name":"Software Engineering Institute","ror":"https://ror.org/01xqjjn94","country_code":"US","type":"facility","lineage":["https://openalex.org/I114772536","https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Nick Winski","raw_affiliation_strings":["Software Engineering Institute, Carnegie Mellon University, Pittsburgh, Pennsylvania, USA"],"affiliations":[{"raw_affiliation_string":"Software Engineering Institute, Carnegie Mellon University, Pittsburgh, Pennsylvania, USA","institution_ids":["https://openalex.org/I114772536","https://openalex.org/I74973139"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5098959775","display_name":"Andrew O. Mellinger","orcid":"https://orcid.org/0009-0000-5440-7664"},"institutions":[{"id":"https://openalex.org/I114772536","display_name":"Software Engineering Institute","ror":"https://ror.org/01xqjjn94","country_code":"US","type":"facility","lineage":["https://openalex.org/I114772536","https://openalex.org/I74973139"]},{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Andrew O. Mellinger","raw_affiliation_strings":["Software Engineering Institute, Carnegie Mellon University, Pittsburgh, Pennsylvania, USA"],"affiliations":[{"raw_affiliation_string":"Software Engineering Institute, Carnegie Mellon University, Pittsburgh, Pennsylvania, USA","institution_ids":["https://openalex.org/I114772536","https://openalex.org/I74973139"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":12,"corresponding_author_ids":["https://openalex.org/A5037586166"],"corresponding_institution_ids":["https://openalex.org/I114772536","https://openalex.org/I74973139"],"apc_list":null,"apc_paid":null,"fwci":1.0632,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":{"value":0.79938165,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":96,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"103","last_page":"105"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.996399998664856,"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":0.996399998664856,"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":0.9955000281333923,"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"}},{"id":"https://openalex.org/T11636","display_name":"Artificial Intelligence in Healthcare and Education","score":0.9868000149726868,"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/computer-science","display_name":"Computer science","score":0.45303189754486084}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.45303189754486084}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3639477.3639720","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3639477.3639720","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3639477.3639720","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 46th International Conference on Software Engineering: Software Engineering in Practice","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3639477.3639720","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3639477.3639720","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3639477.3639720","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 46th International Conference on Software Engineering: Software Engineering in Practice","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":false},"content_urls":{"pdf":"https://content.openalex.org/works/W4399213744.pdf"},"referenced_works_count":8,"referenced_works":["https://openalex.org/W1593271688","https://openalex.org/W2110171129","https://openalex.org/W2155822737","https://openalex.org/W3081168214","https://openalex.org/W3129831491","https://openalex.org/W3154155772","https://openalex.org/W4378189609","https://openalex.org/W4387064039"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2748952813","https://openalex.org/W2390279801","https://openalex.org/W2358668433","https://openalex.org/W4396701345","https://openalex.org/W2376932109","https://openalex.org/W2001405890","https://openalex.org/W4396696052","https://openalex.org/W2382290278","https://openalex.org/W4395014643"],"abstract_inverted_index":{"Large":[0],"Language":[1],"Models":[2],"(LLMs)":[3],"promise":[4],"strategic":[5],"benefit":[6],"for":[7],"numerous":[8],"application":[9],"domains.":[10],"The":[11],"current":[12],"state-of-the-art":[13],"in":[14,27,69,93],"LLMs,":[15],"however,":[16],"lacks":[17],"the":[18,37,56],"trust,":[19],"security,":[20],"and":[21,42,78,86,90,95,106],"reliability":[22],"which":[23],"prohibits":[24],"their":[25],"use":[26],"high":[28,48,70],"stakes":[29,49,71],"applications.":[30],"To":[31],"address":[32],"this,":[33],"our":[34],"work":[35],"investigated":[36],"challenges":[38,58,74,82,92],"of":[39,97],"developing,":[40],"deploying,":[41],"assessing":[43],"LLMs":[44,65],"within":[45],"a":[46],"specific":[47],"application,":[50],"intelligence":[51],"reporting":[52],"workflows.":[53],"We":[54,99],"identified":[55],"following":[57],"that":[59,101],"need":[60],"to":[61,114,116],"be":[62,67],"addressed":[63],"before":[64],"can":[66],"used":[68],"applications:":[72],"(1)":[73],"with":[75,83],"unverified":[76],"data":[77,79],"leakage,":[80],"(2)":[81],"fine":[84],"tuning":[85],"inference":[87],"at":[88],"scale,":[89],"(3)":[91],"reproducibility":[94],"assessment":[96,107],"LLMs.":[98,120],"argue":[100],"researchers":[102],"should":[103],"prioritize":[104],"test":[105],"metrics,":[108],"as":[109],"better":[110],"metrics":[111],"will":[112],"lead":[113],"insight":[115],"further":[117],"improve":[118],"these":[119]},"counts_by_year":[{"year":2025,"cited_by_count":3}],"updated_date":"2026-03-20T23:20:44.827607","created_date":"2025-10-10T00:00:00"}