Skip to content
conftrace_

causal mediation analysis

31 papers

Explore in graph

Also known as

CMA

Co-occurring keywords · papers mentioning both

language model (6) vision-language model (5) large language model (4) gender bia (4) attention head (4) natural direct effect (3) natural indirect effect (3) neural network (3) neuron analysis (3) mechanistic interpretability (3)

Papers

Sparse Interventions in Language Models with Differentiable Masking EMNLP 2022 Testing Pre-trained Language Models’ Understanding of Distributivity via Causal Mediation Analysis EMNLP 2022 What changed? Investigating Debiasing Methods using Causal Mediation Analysis NAACL 2022 Causal Analysis of Syntactic Agreement Mechanisms in Neural Language Models ACL 2021 Text as Causal Mediators: Research Design for Causal Estimates of Differential Treatment of Social Groups via Language Aspects EMNLP 2021 Investigating Gender Bias in Language Models Using Causal Mediation Analysis NeurIPS 2020