https://9p7pzq3jbl.execute-api.us-east-1.amazonaws.com/ProdStage Skip to main content
Publications
Advanced Search

View metadata

dc.titleDocumenting Differences Between Humans and AI in High-Stakes Decisions: A Labor Market Turing Test
dc.contributor.authorAbril Arteaga, Andres Sebastian
dc.contributor.authorRangel, Marcos
dc.contributor.authorZanoni, Wladimir
dc.contributor.orgunitCountry Department Andean Group
dc.coverageEcuador
dc.date.available2025-09-29T00:09:00
dc.date.issue2025-09-29T00:09:00
dc.description.abstractWe developed a Labor Market Turing Test (LMTT) to measure human-AI decision alignment using data from 277 human recruiters engaged in a field experiment set in Quito, Ecuador. We augmented the pool of recruiters by creating AI teams, each of which with differing impersonation of human-like traits, and compared their choices to humans and a benchmark AI model. While AI teams were more consistent, they selected candidates with a pattern that markedly different from human choices. In fact, random decisions mir- rored human choices more closely than our most human-like AI agents. These findings reveal a fundamental tension between algorithmic consistency and human judgment. That humans were closer to a random process when com- paring candidates with equal productivity might be seen as a fairer outcome. Our LMTT framework, which involves isolating and estimating a machina la- tent trait, provides a quantitative tool for assessing human-AI alignment which can be employed across critical domains, such as healthcare, justice, and edu- cation, thereby informing the design and AI governance.
dc.format.extent53
dc.identifier.doihttp://dx.doi.org/10.18235/0013729
dc.identifier.urlhttps://publications.iadb.org/publications/english/document/Documenting-Differences-Between-Humans-and-AI-in-High-Stakes-Decisions-A-Labor-Market-Turing-Test.pdf
dc.language.isoen
dc.publisherInter-American Development Bank
dc.subjectArtificial Intelligence
dc.subjectLabor Market
dc.subjectPopulation Aging
dc.subjectHigher Education
dc.subjectMigrant
dc.subjectWomen
dc.subjectKnowledge
dc.subject.jelcodeJ71 - Discrimination
dc.subject.jelcodeM51 - Firm Employment Decisions • Promotions
dc.subject.jelcodeC91 - Laboratory, Individual Behavior
dc.subject.keywordsAlgorithmic Fairness;Human-AI Alignment;Latent Trait Analysis
dc.typeWorking Papers
idb.identifier.pubnumberIDB-WP-01740
idb.operationRG-T4369
Return to Publication