"Probing Classifiers are Unreliable for Concept Removal and Detection."

Abhinav Kumar, Chenhao Tan, Amit Sharma (2022)

Details and statistics

DOI: 10.48550/ARXIV.2207.04153

access: open

type: Informal or Other Publication

metadata version: 2022-07-13

a service of  Schloss Dagstuhl - Leibniz Center for Informatics