Influence Tuning: Demoting Spurious Correlations via Instance Attribution and Instance-Driven Updates

Among the most critical limitations of deep learning NLP models are their lack of interpretability, and their reliance on spurious correlations. Prior work proposed various approaches to interpreting the black-box models to unveil the spurious correlations, but the research was primarily used in hum...

Ausführliche Beschreibung

Bibliographische Detailangaben

Hauptverfasser:	Han, Xiaochuang, Tsvetkov, Yulia
Format:	Artikel
Sprache:	eng
Schlagworte:	Computer Science - Computation and Language
Online-Zugang:	Volltext bestellen
Tags:	Tag hinzufügen Keine Tags, Fügen Sie den ersten Tag hinzu!