Improving Causal Interventions in Amnesic Probing with Mean Projection or LEACE
This addresses a technical bottleneck in causal intervention methods for NLP researchers, but it is incremental as it builds on existing amnesic probing techniques.
The paper tackles the problem of random modifications introduced by Iterative Nullspace Projection (INLP) in amnesic probing, showing that Mean Projection (MP) and LEACE remove target information more precisely, improving behavioral explanations.
Amnesic probing is a technique used to examine the influence of specific linguistic information on the behaviour of a model. This involves identifying and removing the relevant information and then assessing whether the model's performance on the main task changes. If the removed information is relevant, the model's performance should decline. The difficulty with this approach lies in removing only the target information while leaving other information unchanged. It has been shown that Iterative Nullspace Projection (INLP), a widely used removal technique, introduces random modifications to representations when eliminating target information. We demonstrate that Mean Projection (MP) and LEACE, two proposed alternatives, remove information in a more targeted manner, thereby enhancing the potential for obtaining behavioural explanations through Amnesic Probing.