"Unlearning Reveals the Influential Training Data of Language Models."

Masaru Isonuma, Ivan Titov (2024)

Details and statistics

DOI: 10.48550/ARXIV.2401.15241

access: open

type: Informal or Other Publication

metadata version: 2024-02-06

a service of  Schloss Dagstuhl - Leibniz Center for Informatics