ER-Test: Evaluating Explanation Regularization Methods for Language Models

By explaining how humans would solve a given task, human rationales can provide strong learning signal for neural language models (LMs). Explanation regularization (ER) aims to improve LM generalization by pushing the LM's machine rationales (Which input tokens did the LM focus on?) to align wi...

Ausführliche Beschreibung

Bibliographische Detailangaben

Veröffentlicht in:	arXiv.org 2023-02
Hauptverfasser:	Joshi, Brihi, Chan, Aaron, Liu, Ziyi, Nie, Shaoliang, Sanjabi, Maziar, Hamed Firooz, Ren, Xiang
Format:	Artikel
Sprache:	eng
Schlagworte:	Criteria Datasets Functional testing Questions Regularization Regularization methods Training
Online-Zugang:	Volltext
Tags:	Tag hinzufügen Keine Tags, Fügen Sie den ersten Tag hinzu!