# A Perspective on Explainable Artificial Intelligence Methods: SHAP and LIME

arXiv: https://arxiv.org/abs/2305.02012 · HTML: https://mlsanity.com/paper/2305.02012/

## Key facts

- Cited by 42 papers in the map (data through 14 Oct 2026).
- Builds on 9 of its 31 references that are in the map.
- First posted on arXiv 3 May 2023.

## Builds on (most cited first, 9 of 9)

- [A Unified Approach to Interpreting Model Predictions](https://mlsanity.com/paper/1705.07874/) (2017)
- ["Why Should I Trust You?": Explaining the Predictions of Any Classifier](https://mlsanity.com/paper/1602.04938/) (2016)
- [Fooling LIME and SHAP: Adversarial Attacks on Post hoc Explanation Methods](https://mlsanity.com/paper/1911.02508/) (2019)
- [GraphLIME: Local Interpretable Model Explanations for Graph Neural Networks](https://mlsanity.com/paper/2001.06216/) (2020)
- [Explaining individual predictions when features are dependent: More accurate approximations to Shapley values](https://mlsanity.com/paper/1903.10464/) (2019)
- [General Pitfalls of Model-Agnostic Interpretation Methods for Machine Learning Models](https://mlsanity.com/paper/2007.04131/) (2020)
- [Explaining black box decisions by Shapley cohort refinement](https://mlsanity.com/paper/1911.00467/) (2019)
- [What's in a GitHub Star? Understanding Repository Starring Practices in a Social Coding Platform](https://mlsanity.com/paper/1811.07643/) (2018)
- [Characterizing the contribution of dependent features in XAI methods](https://mlsanity.com/paper/2304.01717/) (2023)

## Built on by (most cited first, 30 of 42)

- [TRiSM for Agentic AI: A Review of Trust, Risk, and Security Management in LLM-based Agentic Multi-Agent Systems](https://mlsanity.com/paper/2506.04133/) (2025)
- [Detecting Linguistic Indicators for Stereotype Assessment with Large Language Models](https://mlsanity.com/paper/2502.19160/) (2025)
- [UbiQTree: Uncertainty Quantification in XAI with Tree Ensembles](https://mlsanity.com/paper/2508.09639/) (2025)
- [Exploring Convolutional Neural Networks for Rice Grain Classification: An Explainable AI Approach](https://mlsanity.com/paper/2505.05513/) (2025)
- [Ethical AI: Towards Defining a Collective Evaluation Framework](https://mlsanity.com/paper/2506.00233/) (2025)
- [From Prototypes to Sparse ECG Explanations: SHAP-Driven Counterfactuals for Multivariate Time-Series Multi-class Classification](https://mlsanity.com/paper/2510.19514/) (2025)
- [Selective Explanations](https://mlsanity.com/paper/2405.19562/) (2024)
- [Explainable AI for Enhancing Efficiency of DL-based Channel Estimation](https://mlsanity.com/paper/2407.07009/) (2024)
- [Detecting anxiety and depression in dialogues: a multi-label and explainable approach](https://mlsanity.com/paper/2412.17651/) (2024)
- [From XAI to Stories: A Factorial Study of LLM-Generated Explanation Quality](https://mlsanity.com/paper/2601.02224/) (2026)
- [Are Linear Regression Models White Box and Interpretable?](https://mlsanity.com/paper/2407.12177/) (2024)
- [Interpretable Multimodal Learning for Tumor Protein-Metal Binding: Progress, Challenges, and Perspectives](https://mlsanity.com/paper/2504.03847/) (2025)
- [Interpretable SHAP-bounded Bayesian Optimization for Underwater Acoustic Metamaterial Coating Design](https://mlsanity.com/paper/2505.06519/) (2025)
- [Spatio-Temporal Forecasting of Retaining Wall Deformation: Mitigating Error Accumulation via Multi-Resolution ConvLSTM Stacking Ensemble](https://mlsanity.com/paper/2603.10453/) (2026)
- [Trustworthy Clinical Decision Support Using Meta-Predicates and Domain-Specific Languages](https://mlsanity.com/paper/2604.21263/) (2026)
- [Improving Electrolyte Performance for Target Cathode Loading Using Interpretable Data-Driven Approach](https://mlsanity.com/paper/2409.01989/) (2024)
- [AI Learning Algorithms: Deep Learning, Hybrid Models, and Large-Scale Model Integration](https://mlsanity.com/paper/2410.09186/) (2024)
- [From Abstract to Actionable: Pairwise Shapley Values for Explainable AI](https://mlsanity.com/paper/2502.12525/) (2025)
- [Graph Attention Networks Unleashed: A Fast and Explainable Vulnerability Assessment Framework for Microgrids](https://mlsanity.com/paper/2503.00786/) (2025)
- [AI Biases as Asymmetries: A Review to Guide Practice](https://mlsanity.com/paper/2503.07326/) (2025)
- [TaylorPODA: A Taylor Expansion-Based Method to Improve Post-Hoc Attributions for Opaque Models](https://mlsanity.com/paper/2507.10643/) (2025)
- [Position: Intelligent Coding Systems Should Write Programs with Justifications](https://mlsanity.com/paper/2508.06017/) (2025)
- [EVO-LRP: Evolutionary Optimization of LRP for Interpretable Model Explanations](https://mlsanity.com/paper/2509.23585/) (2025)
- [Explainable e-sports win prediction through Machine Learning classification in streaming](https://mlsanity.com/paper/2510.19671/) (2025)
- [Bridging Accuracy and Interpretability: Deep Learning with XAI for Breast Cancer Detection](https://mlsanity.com/paper/2510.21780/) (2025)
- [Predicting California Bearing Ratio with Ensemble and Neural Network Models: A Case Study from Turkiye](https://mlsanity.com/paper/2512.08340/) (2025)
- [Generalization and Feature Attribution in Machine Learning Models for Crop Yield and Anomaly Prediction in Germany](https://mlsanity.com/paper/2512.15140/) (2025)
- [UbiQVision: Quantifying Uncertainty in XAI for Image Recognition](https://mlsanity.com/paper/2512.20288/) (2025)
- [Stage-specific cancer survival prediction enriched by explainable machine learning](https://mlsanity.com/paper/2601.03977/) (2026)
- [Bayesian Integration of Nonlinear Incomplete Clinical Data](https://mlsanity.com/paper/2602.01924/) (2026)

## Abstract (arXiv)

eXplainable artificial intelligence (XAI) methods have emerged to convert the black box of machine learning (ML) models into a more digestible form. These methods help to communicate how the model works with the aim of making ML models more transparent and increasing the trust of end-users into their output. SHapley Additive exPlanations (SHAP) and Local Interpretable Model Agnostic Explanation (LIME) are two widely used XAI methods, particularly with tabular data. In this perspective piece, we discuss the way the explainability metrics of these two methods are generated and propose a framework for interpretation of their outputs, highlighting their weaknesses and strengths. Specifically, we discuss their outcomes in terms of model-dependency and in the presence of collinearity among the features, relying on a case study from the biomedical domain (classification of individuals with or without myocardial infarction). The results indicate that SHAP and LIME are highly affected by the adopted ML model and feature collinearity, raising a note of caution on their usage and interpretation.