REVIEW 5 cited by
A Benchmark for Interpretability Methods in Deep Neural Networks
Not yet reviewed by Pith; the record is open.
This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.
SPECIMEN: schema-true, not a live event
T0 review · schema-true
One-sentence machine reading of the paper's core claim.
pith:XXXXXXXX · record.json · timestamp
read the original abstract
We propose an empirical measure of the approximate accuracy of feature importance estimates in deep neural networks. Our results across several large-scale image classification datasets show that many popular interpretability methods produce estimates of feature importance that are not better than a random designation of feature importance. Only certain ensemble based approaches---VarGrad and SmoothGrad-Squared---outperform such a random assignment of importance. The manner of ensembling remains critical, we show that some approaches do no better then the underlying method but carry a far higher computational burden.
Forward citations
Cited by 5 Pith papers
-
On Spectral Properties of Gradient-based Explanation Methods
Gradient-based explanations behave like frequency-band selectors: the gradient acts as a high-pass filter, perturbation as a low-pass filter, and their combination creates explanations that shift with the perturbation scale.
-
A Super-pixel-based Approach to the Stable Interpretation of Neural Networks
Averaging saliency values within super-pixel groups reduces the variance and improves the stability and generalizability of gradient-based interpretation maps.
-
From Features to Actions: Explainability in Traditional and Agentic AI Systems
Attribution explanations that work for static classifiers do not diagnose failures in multi-step AI agents; trace-grounded rubric evaluation does, with state-tracking inconsistency 2.7x more common in failed agent runs.
-
On the Complexity-Faithfulness Trade-off of Gradient-Based Explanations
The paper introduces EF and ΔEF as spectral metrics, but ΔEF is derived from EF, making the complexity-faithfulness trade-off partly tautological.
-
New Faithfulness-Centric Interpretability Paradigms for Natural Language Processing
The thesis shows that randomly masking input tokens during fine-tuning makes post-hoc explanations of NLP models consistently faithful under an erasure-based faithfulness metric.
Discussion (0). Continue with ORCID to comment.