"Faithful to What?" On the Limits of Fidelity-Based Explanations

Jackson Eshbaugh

Keywords: interpretability, explanation fidelity, explanation evaluation, surrogate models, linear probes, faithfulness vs. accuracy, measurement validity

TL;DR: Surrogate explanations can achieve high fidelity to a neural network while failing to capture the task-relevant structure that drives predictive performance, revealing a key limitation of fidelity-based explanation metrics.

Abstract: In explainable AI, surrogate models are commonly evaluated by their fidelity to a neural network's predictions. Fidelity, however, measures alignment to a learned model rather than alignment to the data-generating signal underlying the task. This work introduces the linearity score $\lambda(f)$, a diagnostic that quantifies the extent to which a regression network's input--output behavior is linearly decodable. $\lambda(f)$ is defined as an $R^2$ measure of surrogate fit to the network. Across synthetic and real-world regression datasets, we find that surrogates can achieve high fidelity to a neural network while failing to recover the predictive gains that distinguish the network from simpler models. In several cases, high-fidelity surrogates underperform even linear baselines trained directly on the data. These results demonstrate that explaining a model's behavior is not equivalent to explaining the task-relevant structure of the data, highlighting a limitation of fidelity-based explanations when used to reason about predictive performance.

Anonymization: This submission has been anonymized for double-blind review via the removal of identifying information such as names, affiliations, and identifying URLs.

Style Files: I have used the style files.

Submission Number: 68