Causal Proxy Models for Concept-Based Model Explanations. (arXiv:2209.14279v1 [cs.CL])

Explainability methods for NLP systems encounter a version of the fundamental
problem of causal inference: for a given ground-truth input text, we never
truly observe the counterfactual texts necessary for isolating the causal
effects of model representations on outputs. In response, many explainability
methods make no use of counterfactual texts, assuming they will be unavailable.
In this paper, we show that robust causal explainability methods can be created
using approximate counterfactuals, which can be written by humans to
approximate a …

arxiv concept