LIME

An explainable AI technique, introduced by Ribeiro et al. in 2016, that approximates any black-box model's behaviour around a single prediction by fitting a simple interpretable model (usually sparse linear regression) to perturbed versions of the input. The resulting feature weights are presented to users as a small list of most-important features. LIME is model-agnostic and handles text, tabular, and image inputs, but like most XAI methods its visual outputs are typically charts or highlighted image regions that are not directly accessible to blind or low-vision users.