"Interpreting Pretrained Language Models via Concept Bottlenecks."

Zhen Tan et al. (2023)

Details and statistics

DOI: 10.48550/ARXIV.2311.05014

access: open

type: Informal or Other Publication

metadata version: 2023-11-14

a service of  Schloss Dagstuhl - Leibniz Center for Informatics