Removing Spurious Concepts from Neural Network Representations via Joint Subspace Estimation

18 October 2023

Papers citing "Removing Spurious Concepts from Neural Network Representations via Joint Subspace Estimation"

4 / 4 papers shown

Title
Are All Spurious Features in Natural Language Alike? An Analysis through a Causal Lens Nitish Joshi X. Pan Hengxing He CML 26 28 0 25 Oct 2022
Linear Adversarial Concept Erasure Shauli Ravfogel Michael Twiton Yoav Goldberg Ryan Cotterell KELM 62 56 0 28 Jan 2022
Probing Classifiers: Promises, Shortcomings, and Advances Yonatan Belinkov 219 291 0 24 Feb 2021
An Investigation of Why Overparameterization Exacerbates Spurious Correlations Shiori Sagawa Aditi Raghunathan Pang Wei Koh Percy Liang 128 368 0 09 May 2020