# Epistemic values in feature importance methods: Lessons from feminist epistemology

arXiv: https://arxiv.org/abs/2101.12737 · HTML: https://mlsanity.com/paper/2101.12737/

## Key facts

- Cited by 11 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 29 Jan 2021.

## Built on by (most cited first, 11 of 11)

- [Ethical and social risks of harm from Language Models](https://mlsanity.com/paper/2112.04359/) (2021)
- [Auditing large language models: a three-layered approach](https://mlsanity.com/paper/2302.08500/) (2023)
- [Subverting machines, fluctuating identities: Re-learning human categorization](https://mlsanity.com/paper/2205.13740/) (2022)
- [Equalizing Credit Opportunity in Algorithms: Aligning Algorithmic Fairness Research with U.S. Fair Lending Regulation](https://mlsanity.com/paper/2210.02516/) (2022)
- [What will it take to generate fairness-preserving explanations?](https://mlsanity.com/paper/2106.13346/) (2021)
- [Data Feminism for AI](https://mlsanity.com/paper/2405.01286/) (2024)
- [SHAP-based Explanations are Sensitive to Feature Representation](https://mlsanity.com/paper/2505.08345/) (2025)
- [Towards Feminist Intersectional XAI: From Explainability to Response-Ability](https://mlsanity.com/paper/2305.03375/) (2023)
- [Regression Trees Know Calculus](https://mlsanity.com/paper/2405.13846/) (2024)
- [Fuck the Algorithm: Conceptual Issues in Algorithmic Bias](https://mlsanity.com/paper/2505.13509/) (2025)
- [Emergent, not Immanent: A Baradian Reading of Explainable AI](https://mlsanity.com/paper/2601.15029/) (2026)

## Abstract (arXiv)

As the public seeks greater accountability and transparency from machine learning algorithms, the research literature on methods to explain algorithms and their outputs has rapidly expanded. Feature importance methods form a popular class of explanation methods. In this paper, we apply the lens of feminist epistemology to recent feature importance research. We investigate what epistemic values are implicitly embedded in feature importance methods and how or whether they are in conflict with feminist epistemology. We offer some suggestions on how to conduct research on explanations that respects feminist epistemic values, taking into account the importance of social context, the epistemic privileges of subjugated knowers, and adopting more interactional ways of knowing.