lime

The study introduces SHAP-RTL, a rendering layer that corrects the visualization of SHAP and LIME explanations for right-to-left languages, addressing issues like token sequence and script shaping while preserving original attribution values.

The paper proposes a new evaluation method for machine learning explanations by converting explanations into predictors and testing their ability to reproduce model predictions. It demonstrates that the effectiveness of explanation methods like SHAP and PDP depends on the independence of features in the data.

The paper introduces a framework for integrating explainable AI into CRM systems for customer churn prediction in telecommunications, benchmarking classifiers and using SHAP and LIME for interpretable predictions to enhance retention strategies.

This paper proposes BREAD, a scalable baseline-referenced explanation method for diagnosing anomalies in AI-based statistical process monitoring, with theoretical guarantees showing higher faithfulness than LIME under mean-shift anomalies.

This paper builds a multi-scale stacking ensemble for credit risk scoring and audits LLM-generated explanations, finding that ranking gains are real but small while the narrative explanations are often unfaithful, with SHAP and LIME agreeing on important features but not their order or sign.

This paper presents a comparative evaluation of post-hoc analysis methods (Random Forest surrogate, LIME, PCA) for detecting structured patterns in clustering results, using synthetic datasets with injected patterns. It finds that none of the methods consistently detects all pattern types, highlighting a gap in existing explainability tools.

This paper systematically evaluates how post-training quantization affects the interpretability of CNN models using Grad-CAM and LIME, revealing that classification accuracy is not a reliable indicator of interpretability stability and that architecture selection is critical for trustworthy deployment.

This paper proposes using generative inpainting to create photorealistic perturbations for LIME, improving the quality of explanations by avoiding out-of-distribution artifacts common in traditional occlusion methods.

This article provides a systematic and comprehensive overview of AI explainability, covering its needs (debugging, compliance, safety), classic methods, and cutting-edge challenges, emphasizing that faithful explanations are more important than plausible ones.

This paper introduces CoRA, a GRPO-based reinforcement learning framework that aligns LLM confidence with generated rationales to improve the reliability of chain-of-thought reasoning, achieving up to 26.51% reduction in misalignment error across multiple benchmarks.