LIME

Mainstream XAI methods include LIME (Local Interpretable Model-agnostic Explanations), SHAP (game-theory-based feature contribution value calculation), attention visualization, and others.

LIME and SHAP are methods in the field of explainable AI (XAI) that attempt to explain model behavior post hoc.

LIME (Local Interpretable Model-Agnostic Explanations) and SHAP (SHapley Additive exPlanations) are the primary tools for providing post-hoc explanations for complex black-box models.

LIME explains individual predictions by generating a perturbed dataset around the input sample to train a local linear approximation model, while SHAP provides feature attribution based on game-theoretic Shapley values; both are model-agnostic techniques.

LIME通过在目标样本周围构造扰动数据集，训练局部可解释的线性模型来近似复杂模型的局部行为

Providing interpretability information (such as feature attributions generated by LIME or SHAP) can effectively counter automation bias.

Pixel-level attribution methods such as LIME, SHAP, and Grad-CAM use pixels or regions as the unit of explanation rather than semantic concepts familiar to humans.

SHAP and LIME are both post-hoc explanation frameworks that do not modify the model itself, but instead generate explanations after predictions are made.

The nine evaluated XAI methods cover gradient-based methods (Vanilla Gradient, Integrated Gradients), perturbation-based methods (LIME, KernelSHAP), and propagation-rule-based methods (LRP).

Mainstream methods such as LIME and SHAP treat maximizing local fidelity as their optimization objective by design.

The framework incorporates LIME (Local Interpretable Model-agnostic Explanations) to explain model predictions by highlighting the text features that have the greatest influence on the classification results.

LIME works by applying small perturbations to the input within the local neighborhood of the sample to be explained, observing changes in model output, and then approximating local behavior with a simple linear model; it is a model-agnostic method that can provide explanations for any black-box model.

LIME provides local rather than global explanations, guaranteeing reliability only in the vicinity of the current sample and cannot fully describe the model's decision logic across the entire feature space.

Academia has developed explanation methods such as SHAP values and LIME, but these tools currently struggle to provide complete explanation paths sufficient to support high-stakes decisions.

Mainstream explainable AI techniques include post-hoc explanation methods such as SHAP (game-theory-based Shapley value attribution), LIME (local interpretable model-agnostic explanations), and attention mechanism visualization, as well as inherently interpretable models such as decision trees, logistic regression, and rule lists.

SHAP and LIME are post-hoc explanation techniques for addressing algorithmic interpretability challenges.

Explainable AI (XAI) techniques such as SHAP values and LIME methods attempt to make algorithmic decision logic understandable to humans, but their application to complex deep learning models still faces challenges.

SHAP values and LIME are commonly used local interpretability methods capable of quantifying each feature's contribution to a single decision.

LIME由2016年Ribeiro等人提出，其重大缺陷是解释的不稳定性，对同一样本多次运行可能得到不同解释