"CausalGym: Benchmarking causal interpretability methods on linguistic tasks."

Aryaman Arora, Dan Jurafsky, Christopher Potts (2024)

Details and statistics

DOI: 10.48550/ARXIV.2402.12560

access: open

type: Informal or Other Publication

metadata version: 2024-03-21

a service of  Schloss Dagstuhl - Leibniz Center for Informatics