# In Defence of Post-hoc Explainability

arXiv: https://arxiv.org/abs/2412.17883 · HTML: https://mlsanity.com/paper/2412.17883/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 21 of its 44 references that are in the map.
- First posted on arXiv 23 Dec 2024.

## Builds on (most cited first, 21 of 21)

- [Towards A Rigorous Science of Interpretable Machine Learning](https://mlsanity.com/paper/1702.08608/) (2017)
- [Progress measures for grokking via mechanistic interpretability](https://mlsanity.com/paper/2301.05217/) (2023)
- [The Mythos of Model Interpretability](https://mlsanity.com/paper/1606.03490/) (2016)
- [Captum: A unified and generic model interpretability library for PyTorch](https://mlsanity.com/paper/2009.07896/) (2020)
- [A Benchmark for Interpretability Methods in Deep Neural Networks](https://mlsanity.com/paper/1806.10758/) (2018)
- [Fooling LIME and SHAP: Adversarial Attacks on Post hoc Explanation Methods](https://mlsanity.com/paper/1911.02508/) (2019)
- [Explainable AI (XAI): A Systematic Meta-Survey of Current Challenges and Future Opportunities](https://mlsanity.com/paper/2111.06420/) (2021)
- [The Dangers of Post-hoc Interpretability: Unjustified Counterfactual Explanations](https://mlsanity.com/paper/1907.09294/) (2019)
- [Impossibility Theorems for Feature Attribution](https://mlsanity.com/paper/2212.11870/) (2022)
- [Post hoc Explanations may be Ineffective for Detecting Unknown Spurious Correlation](https://mlsanity.com/paper/2212.04629/) (2022)
- [Issues with post-hoc counterfactual explanations: a discussion](https://mlsanity.com/paper/1906.04774/) (2019)
- [Evaluating Explanation Without Ground Truth in Interpretable Machine Learning](https://mlsanity.com/paper/1907.06831/) (2019)
- [Finding the right XAI method -- A Guide for the Evaluation and Ranking of Explainable AI Methods in Climate Science](https://mlsanity.com/paper/2303.00652/) (2023)
- [Local vs. Global Interpretability: A Computational Complexity Perspective](https://mlsanity.com/paper/2406.02981/) (2024)
- [Scientific Inference With Interpretable Machine Learning: Analyzing Models to Learn About Real-World Phenomena](https://mlsanity.com/paper/2206.05487/) (2022)
- [The Computational Complexity of Circuit Discovery for Inner Interpretability](https://mlsanity.com/paper/2410.08025/) (2024)
- [Interpretability Needs a New Paradigm](https://mlsanity.com/paper/2405.05386/) (2024)
- [Social Construction of XAI: Do We Need One Definition to Rule Them All?](https://mlsanity.com/paper/2211.06499/) (2022)
- [Revisiting the robustness of post-hoc interpretability methods](https://mlsanity.com/paper/2407.19683/) (2024)
- [Artificial Neural Nets and the Representation of Human Concepts](https://mlsanity.com/paper/2312.05337/) (2023)
- [Structural Risk Minimization for Learning Nonlinear Dynamics](https://mlsanity.com/paper/2309.16527/) (2023)

## Built on by (most cited first, 1 of 1)

- [Finding Multiple Interpretations in Datasets](https://mlsanity.com/paper/2606.12277/) (2026)

## Abstract (arXiv)

This position paper defends post-hoc explainability methods as legitimate tools for scientific knowledge production in machine learning. Addressing criticism of these methods' reliability and epistemic status, we develop a philosophical framework grounded in mediated understanding and bounded factivity. We argue that scientific insights can emerge through structured interpretation of model behaviour without requiring complete mechanistic transparency, provided explanations acknowledge their approximative nature and undergo rigorous empirical validation. Through analysis of recent biomedical ML applications, we demonstrate how post-hoc methods, when properly integrated into scientific practice, generate novel hypotheses and advance phenomenal understanding.