Matches in SemOpenAlex for { <https://semopenalex.org/work/W4320342906> ?p ?o ?g. }
Showing items 1 to 94 of
94
with 100 items per page.
- W4320342906 abstract "Machine learning models with high accuracy on test data can still produce systematic failures, such as harmful biases and safety issues, when deployed in the real world. To detect and mitigate such failures, practitioners run behavioral evaluation of their models, checking model outputs for specific types of inputs. Behavioral evaluation is important but challenging, requiring that practitioners discover real-world patterns and validate systematic failures. We conducted 18 semi-structured interviews with ML practitioners to better understand the challenges of behavioral evaluation and found that it is a collaborative, use-case-first process that is not adequately supported by existing task- and domain-specific tools. Using these findings, we designed zeno, a general-purpose framework for visualizing and testing AI systems across diverse use cases. In four case studies with participants using zeno on real-world models, we found that practitioners were able to reproduce previous manual analyses and discover new systematic failures." @default.
- W4320342906 created "2023-02-13" @default.
- W4320342906 creator A5011301944 @default.
- W4320342906 creator A5022664382 @default.
- W4320342906 creator A5029768722 @default.
- W4320342906 creator A5053097987 @default.
- W4320342906 creator A5060162507 @default.
- W4320342906 creator A5090119454 @default.
- W4320342906 creator A5090310268 @default.
- W4320342906 date "2023-04-19" @default.
- W4320342906 modified "2023-10-02" @default.
- W4320342906 title "Zeno: An Interactive Framework for Behavioral Evaluation of Machine Learning" @default.
- W4320342906 cites W1861492603 @default.
- W4320342906 cites W2028138594 @default.
- W4320342906 cites W2440722286 @default.
- W4320342906 cites W2516678343 @default.
- W4320342906 cites W2767128594 @default.
- W4320342906 cites W2782311202 @default.
- W4320342906 cites W2789415069 @default.
- W4320342906 cites W2898186212 @default.
- W4320342906 cites W2940677186 @default.
- W4320342906 cites W2952602496 @default.
- W4320342906 cites W2974071289 @default.
- W4320342906 cites W3011721937 @default.
- W4320342906 cites W3035507081 @default.
- W4320342906 cites W3100279624 @default.
- W4320342906 cites W3204393347 @default.
- W4320342906 cites W3208416788 @default.
- W4320342906 cites W3212368439 @default.
- W4320342906 cites W4229447062 @default.
- W4320342906 cites W4285113702 @default.
- W4320342906 cites W4312933868 @default.
- W4320342906 doi "https://doi.org/10.1145/3544548.3581268" @default.
- W4320342906 hasPublicationYear "2023" @default.
- W4320342906 type Work @default.
- W4320342906 citedByCount "3" @default.
- W4320342906 countsByYear W43203429062023 @default.
- W4320342906 crossrefType "proceedings-article" @default.
- W4320342906 hasAuthorship W4320342906A5011301944 @default.
- W4320342906 hasAuthorship W4320342906A5022664382 @default.
- W4320342906 hasAuthorship W4320342906A5029768722 @default.
- W4320342906 hasAuthorship W4320342906A5053097987 @default.
- W4320342906 hasAuthorship W4320342906A5060162507 @default.
- W4320342906 hasAuthorship W4320342906A5090119454 @default.
- W4320342906 hasAuthorship W4320342906A5090310268 @default.
- W4320342906 hasBestOaLocation W43203429061 @default.
- W4320342906 hasConcept C107457646 @default.
- W4320342906 hasConcept C111472728 @default.
- W4320342906 hasConcept C111919701 @default.
- W4320342906 hasConcept C119857082 @default.
- W4320342906 hasConcept C127413603 @default.
- W4320342906 hasConcept C134306372 @default.
- W4320342906 hasConcept C138885662 @default.
- W4320342906 hasConcept C154945302 @default.
- W4320342906 hasConcept C201995342 @default.
- W4320342906 hasConcept C2780451532 @default.
- W4320342906 hasConcept C33923547 @default.
- W4320342906 hasConcept C36503486 @default.
- W4320342906 hasConcept C41008148 @default.
- W4320342906 hasConcept C7707877 @default.
- W4320342906 hasConcept C98045186 @default.
- W4320342906 hasConceptScore W4320342906C107457646 @default.
- W4320342906 hasConceptScore W4320342906C111472728 @default.
- W4320342906 hasConceptScore W4320342906C111919701 @default.
- W4320342906 hasConceptScore W4320342906C119857082 @default.
- W4320342906 hasConceptScore W4320342906C127413603 @default.
- W4320342906 hasConceptScore W4320342906C134306372 @default.
- W4320342906 hasConceptScore W4320342906C138885662 @default.
- W4320342906 hasConceptScore W4320342906C154945302 @default.
- W4320342906 hasConceptScore W4320342906C201995342 @default.
- W4320342906 hasConceptScore W4320342906C2780451532 @default.
- W4320342906 hasConceptScore W4320342906C33923547 @default.
- W4320342906 hasConceptScore W4320342906C36503486 @default.
- W4320342906 hasConceptScore W4320342906C41008148 @default.
- W4320342906 hasConceptScore W4320342906C7707877 @default.
- W4320342906 hasConceptScore W4320342906C98045186 @default.
- W4320342906 hasFunder F4320306076 @default.
- W4320342906 hasLocation W43203429061 @default.
- W4320342906 hasLocation W43203429062 @default.
- W4320342906 hasOpenAccess W4320342906 @default.
- W4320342906 hasPrimaryLocation W43203429061 @default.
- W4320342906 hasRelatedWork W1504101963 @default.
- W4320342906 hasRelatedWork W1721086902 @default.
- W4320342906 hasRelatedWork W2180505379 @default.
- W4320342906 hasRelatedWork W2961085424 @default.
- W4320342906 hasRelatedWork W3046775127 @default.
- W4320342906 hasRelatedWork W4285260836 @default.
- W4320342906 hasRelatedWork W4286629047 @default.
- W4320342906 hasRelatedWork W4306321456 @default.
- W4320342906 hasRelatedWork W4306674287 @default.
- W4320342906 hasRelatedWork W4224009465 @default.
- W4320342906 isParatext "false" @default.
- W4320342906 isRetracted "false" @default.
- W4320342906 workType "article" @default.