Which LIME should I trust? Concepts, Challenges, and Solutions
This addresses the problem for researchers and practitioners in AI/ML who are overwhelmed by the growing number of LIME-related methods, helping them identify suitable approaches, though it is incremental as a survey rather than a novel method.
This paper tackles the challenge of navigating the numerous adaptations and enhancements of LIME (Local Interpretable Model-agnostic Explanations) in Explainable AI by providing the first comprehensive survey that categorizes and compares these developments, offering a structured taxonomy and an interactive website for guidance.
As neural networks become dominant in essential systems, Explainable Artificial Intelligence (XAI) plays a crucial role in fostering trust and detecting potential misbehavior of opaque models. LIME (Local Interpretable Model-agnostic Explanations) is among the most prominent model-agnostic approaches, generating explanations by approximating the behavior of black-box models around specific instances. Despite its popularity, LIME faces challenges related to fidelity, stability, and applicability to domain-specific problems. Numerous adaptations and enhancements have been proposed to address these issues, but the growing number of developments can be overwhelming, complicating efforts to navigate LIME-related research. To the best of our knowledge, this is the first survey to comprehensively explore and collect LIME's foundational concepts and known limitations. We categorize and compare its various enhancements, offering a structured taxonomy based on intermediate steps and key issues. Our analysis provides a holistic overview of advancements in LIME, guiding future research and helping practitioners identify suitable approaches. Additionally, we provide a continuously updated interactive website (https://patrick-knab.github.io/which-lime-to-trust/), offering a concise and accessible overview of the survey.