Which LIME should I trust? Concepts, Challenges, and Solutions

2025-03-31

AI Summary

LIME suffers from inherent limitations in fidelity, stability, and domain adaptability, while the proliferation of method variants complicates model selection. To address this, we propose the first comprehensive, lifecycle-spanning taxonomy for LIME enhancement techniques—structured around intermediate computational steps and core conceptual challenges. Through systematic literature review, technical attribution analysis, and taxonomy-driven modeling, we rigorously characterize LIME’s theoretical foundations, intrinsic weaknesses, and evolutionary trajectories. We further release an open-source, interactive knowledge graph platform, dynamically updated to reflect ongoing advances. Our key contributions are: (i) the first multidimensional, decoupled classification framework for LIME improvements, enabling fine-grained method comparison; and (ii) an intuitive, navigable visualization interface that serves as an authoritative, actionable selection guide and a sustainably maintained knowledge infrastructure for XAI researchers and practitioners.

Technology Category

• Machine Learning: Large Multimodal Models (LMMs)
• Knowledge Representation and Reasoning: Computational Complexity of Reasoning
• Data Mining & Knowledge Management: Other Foundations of Data Mining & Knowledge Management

Application Category

• Semantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMs
• Graph Algorithms and Modeling for the Web: Foundation models and LLMs for Web-related graphs
• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking

Abstract

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.

Problem

• Evaluating LIME's fidelity and stability in explanations
• Addressing domain-specific applicability of LIME enhancements
• Navigating and categorizing growing LIME-related research developments

Innovation

• Surveying LIME's foundational concepts and limitations
• Categorizing enhancements via structured taxonomy
• Providing interactive website for updates