Towards Reliable and Faithful Explanations : A Disentanglement-Augmented Approach for Selective Rationalization
The pursuit of model explainability has prompted the selective rationalization (aka, rationale extraction) which can identify important features (i.e., rationales) from the original input to support prediction results. Existing methods typically involve a cascaded approach with a selector responsibl...
Ausführliche Beschreibung
Bibliographische Detailangaben
| Veröffentlicht in: | IEEE transactions on pattern analysis and machine intelligence. - 1979. - 47(2025), 11 vom: 01. Okt., Seite 9906-9921
|
|---|
| 1. Verfasser: |
Yue, Linan
(VerfasserIn) |
|---|
| Weitere Verfasser: |
Liu, Qi,
Du, YiChao,
Wang, Li,
An, Yanqing,
Chen, Enhong |
|---|
| Format: | Online-Aufsatz
|
|---|
| Sprache: | English |
|---|
| Veröffentlicht: |
2025
|
|---|
| Zugriff auf das übergeordnete Werk: | IEEE transactions on pattern analysis and machine intelligence
|
|---|
| Schlagworte: | Journal Article |
|---|