# Machine Learning and Knowledge: Why Robustness Matters

arXiv: https://arxiv.org/abs/2310.19819 · HTML: https://mlsanity.com/paper/2310.19819/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 23 of its 69 references that are in the map.
- First posted on arXiv 23 Oct 2023.

## Builds on (most cited first, 23 of 23)

- [Language Models are Few-Shot Learners](https://mlsanity.com/paper/2005.14165/) (2020)
- [High-Resolution Image Synthesis with Latent Diffusion Models](https://mlsanity.com/paper/2112.10752/) (2021)
- [Grad-CAM: Visual Explanations from Deep Networks via Gradient-based Localization](https://mlsanity.com/paper/1610.02391/) (2016)
- [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)
- [Survey of Hallucination in Natural Language Generation](https://mlsanity.com/paper/2202.03629/) (2022)
- [Shortcut Learning in Deep Neural Networks](https://mlsanity.com/paper/2004.07780/) (2020)
- [WILDS: A Benchmark of in-the-Wild Distribution Shifts](https://mlsanity.com/paper/2012.07421/) (2020)
- [Adversarial Examples Are Not Bugs, They Are Features](https://mlsanity.com/paper/1905.02175/) (2019)
- [One pixel attack for fooling deep neural networks](https://mlsanity.com/paper/1710.08864/) (2017)
- [Measuring Robustness to Natural Distribution Shifts in Image Classification](https://mlsanity.com/paper/2007.00644/) (2020)
- [On Evaluating Adversarial Robustness](https://mlsanity.com/paper/1902.06705/) (2019)
- [Causal Abstractions of Neural Networks](https://mlsanity.com/paper/2106.02997/) (2021)
- [Performative Prediction](https://mlsanity.com/paper/2002.06673/) (2020)
- [The AI Economist: Improving Equality and Productivity with AI-Driven Tax Policies](https://mlsanity.com/paper/2004.13332/) (2020)
- [Theoretical Impediments to Machine Learning With Seven Sparks from the Causal Revolution](https://mlsanity.com/paper/1801.04016/) (2018)
- [Online Human-Bot Interactions: Detection, Estimation, and Characterization](https://mlsanity.com/paper/1703.03107/) (2017)
- [When does dough become a bagel? Analyzing the remaining mistakes on ImageNet](https://mlsanity.com/paper/2205.04596/) (2022)
- [Causally motivated Shortcut Removal Using Auxiliary Labels](https://mlsanity.com/paper/2105.06422/) (2021)
- [Certified Robustness Against Natural Language Attacks by Causal Intervention](https://mlsanity.com/paper/2205.12331/) (2022)
- [Toward Certified Robustness Against Real-World Distribution Shifts](https://mlsanity.com/paper/2206.03669/) (2022)
- [Reasons, Values, Stakeholders: A Philosophical Framework for Explainable Artificial Intelligence](https://mlsanity.com/paper/2103.00752/) (2021)
- [Fairness and robustness in anti-causal prediction](https://mlsanity.com/paper/2209.09423/) (2022)

## Abstract (arXiv)

Trusting machine learning algorithms requires having confidence in their outputs. Confidence is typically interpreted in terms of model reliability, where a model is reliable if it produces a high proportion of correct outputs. However, model reliability does not address concerns about the robustness of machine learning models, such as models relying on the wrong features or variations in performance based on context. I argue that the epistemic dimension of trust can instead be understood through the concept of knowledge, where the trustworthiness of an algorithm depends on whether its users are in the position to know that its outputs are correct. Knowledge requires beliefs to be formed for the right reasons and to be robust to error, so machine learning algorithms can only provide knowledge if they work well across counterfactual scenarios and if they make decisions based on the right features. This, I argue, can explain why we should care about model properties like interpretability, causal shortcut independence, and distribution shift robustness even if such properties are not required for model reliability.