# A review of possible effects of cognitive biases on the interpretation of rule-based machine learning models

arXiv: https://arxiv.org/abs/1804.02969 · HTML: https://mlsanity.com/paper/1804.02969/

## Key facts

- Cited by 22 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 9 Apr 2018.

## Built on by (most cited first, 22 of 22)

- [Fairness via Explanation Quality: Evaluating Disparities in the Quality of Post hoc Explanations](https://mlsanity.com/paper/2205.07277/) (2022)
- [T2VPhysBench: A First-Principles Benchmark for Physical Consistency in Text-to-Video Generation](https://mlsanity.com/paper/2505.00337/) (2025)
- [FAIntbench: A Holistic and Precise Benchmark for Bias Evaluation in Text-to-Image Models](https://mlsanity.com/paper/2405.17814/) (2024)
- [Towards Unifying Evaluation of Counterfactual Explanations: Leveraging Large Language Models for Human-Centric Assessments](https://mlsanity.com/paper/2410.21131/) (2024)
- [Why we need biased AI -- How including cognitive and ethical machine biases can enhance AI systems](https://mlsanity.com/paper/2203.09911/) (2022)
- [Interpretable Learned Emergent Communication for Human-Agent Teams](https://mlsanity.com/paper/2201.07452/) (2022)
- [Why do explanations fail? A typology and discussion on failures in XAI](https://mlsanity.com/paper/2405.13474/) (2024)
- [BIASeD: Bringing Irrationality into Automated System Design](https://mlsanity.com/paper/2210.01122/) (2022)
- [Exploring Qualitative Research Using LLMs](https://mlsanity.com/paper/2306.13298/) (2023)
- [The Roles and Modes of Human Interactions with Automated Machine Learning Systems](https://mlsanity.com/paper/2205.04139/) (2022)
- [MCP-Orchestrated Multi-Agent System for Automated Disinformation Detection](https://mlsanity.com/paper/2508.10143/) (2025)
- [Unpacking Human-AI Interaction in Safety-Critical Industries: A Systematic Literature Review](https://mlsanity.com/paper/2310.03392/) (2023)
- [A survey on bias in machine learning research](https://mlsanity.com/paper/2308.11254/) (2023)
- [Explaining Predictions by Characteristic Rules](https://mlsanity.com/paper/2405.21003/) (2024)
- [Understanding with toy surrogate models in machine learning](https://mlsanity.com/paper/2410.05675/) (2024)
- [Stable and Interpretable Deep Learning for Tabular Data: Introducing InterpreTabNet with the Novel InterpreStability Metric](https://mlsanity.com/paper/2310.02870/) (2023)
- [Identifying and examining machine learning biases on Adult dataset](https://mlsanity.com/paper/2310.09373/) (2023)
- [Meaningless is better: hashing bias-inducing words in LLM prompts improves performance in logical reasoning and statistical learning](https://mlsanity.com/paper/2411.17304/) (2024)
- [Explaining Group Recommendations via Counterfactuals](https://mlsanity.com/paper/2601.16882/) (2026)
- [Personalized Detection of Cognitive Biases in Actions of Users from Their Logs: Anchoring and Recency Biases](https://mlsanity.com/paper/2206.15129/) (2022)
- [Biased Minds Meet Biased AI: How Class Imbalance Shapes Appropriate Reliance and Interacts with Human Base Rate Neglect](https://mlsanity.com/paper/2511.14591/) (2025)
- [Deep Active Re-Labeling: Toward Noise-Resilient Annotation Efficiency](https://mlsanity.com/paper/2606.08718/) (2026)

## Abstract (arXiv)

While the interpretability of machine learning models is often equated with their mere syntactic comprehensibility, we think that interpretability goes beyond that, and that human interpretability should also be investigated from the point of view of cognitive science. The goal of this paper is to discuss to what extent cognitive biases may affect human understanding of interpretable machine learning models, in particular of logical rules discovered from data. Twenty cognitive biases are covered, as are possible debiasing techniques that can be adopted by designers of machine learning algorithms and software. Our review transfers results obtained in cognitive psychology to the domain of machine learning, aiming to bridge the current gap between these two areas. It needs to be followed by empirical studies specifically focused on the machine learning domain.