REVIEW 4 cited by
Bridging Interpretability and Robustness Using LIME-Guided Model Refinement
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
This paper explores the intricate relationship between interpretability and robustness in deep learning models. Despite their remarkable performance across various tasks, deep learning models often exhibit critical vulnerabilities, including susceptibility to adversarial attacks, over-reliance on spurious correlations, and a lack of transparency in their decision-making processes. To address these limitations, we propose a novel framework that leverages Local Interpretable Model-Agnostic Explanations (LIME) to systematically enhance model robustness. By identifying and mitigating the influence of irrelevant or misleading features, our approach iteratively refines the model, penalizing reliance on these features during training. Empirical evaluations on multiple benchmark datasets demonstrate that LIME-guided refinement not only improves interpretability but also significantly enhances resistance to adversarial perturbations and generalization to out-of-distribution data.
Forward citations
Cited by 4 Pith papers
-
Grad-CAM for Vision Transformers: A Systematic Taxonomy and Audit of Methodological Ambiguity in Explainable AI
A systematic audit of 175 papers finds that most uses of Grad-CAM on vision transformers omit the implementation choices needed to reproduce the visual explanation, and introduces a taxonomy to name those choices.
-
Mechanistic Interpretability of LLM Jailbreaks via Internal Attribution Graphs
On Llama-2-7B, path-rerouting magnitude in paired transcoder attribution graphs correlates with jailbreak success (r=0.461), while static node metrics and top-feature ablations do not.
-
Explainable Novel Category Discovery in Semantic Concept Space
xNCD routes novel category discovery through a CLIP-aligned concept bottleneck, matching strong NCD baselines while producing intrinsic cluster- and instance-level concept explanations.
-
Learning to Transmit: Volatility-Aware Predictive Communication for Energy-Efficient IoT Networks
Sensors using volatility-aware studentized residuals plus RLS online adaptation transmit up to 94.7% less IoT data while keeping reconstruction MAE at 0.35°C.
Discussion (0). Continue with ORCID to comment.