# Beneficial and Harmful Explanatory Machine Learning

arXiv: https://arxiv.org/abs/2009.06410 · HTML: https://mlsanity.com/paper/2009.06410/

## Key facts

- Cited by 13 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 9 Sep 2020.

## Built on by (most cited first, 13 of 13)

- [Leveraging Explanations in Interactive Machine Learning: An Overview](https://mlsanity.com/paper/2207.14526/) (2022)
- [Inductive logic programming at 30](https://mlsanity.com/paper/2102.10556/) (2021)
- [Single-Turn Debate Does Not Help Humans Answer Hard Reading-Comprehension Questions](https://mlsanity.com/paper/2204.05212/) (2022)
- [Generating Contrastive Explanations for Inductive Logic Programming Based on a Near Miss Approach](https://mlsanity.com/paper/2106.08064/) (2021)
- [A Critical Review of Inductive Logic Programming Techniques for Explainable AI](https://mlsanity.com/paper/2112.15319/) (2021)
- [Explanatory machine learning for sequential human teaching](https://mlsanity.com/paper/2205.10250/) (2022)
- [Multi-Turn Human-LLM Interaction Through the Lens of a Two-Way Intelligibility Protocol](https://mlsanity.com/paper/2410.20600/) (2024)
- [A Model for Intelligible Interaction Between Agents That Predict and Explain](https://mlsanity.com/paper/2301.01819/) (2023)
- [Boolean matrix logic programming for active learning of gene functions in genome-scale metabolic network models](https://mlsanity.com/paper/2405.06724/) (2024)
- [One-way Explainability Isn't The Message](https://mlsanity.com/paper/2205.08954/) (2022)
- [People Are Highly Cooperative with Large Language Models, Especially When Communication Is Possible or Following Human Interaction](https://mlsanity.com/paper/2507.18639/) (2025)
- [Ultra Strong Machine Learning: LLM-Generated Explanations Do Not Yet Suffice for Teaching Humans Active Learning Strategy](https://mlsanity.com/paper/2509.00961/) (2025)
- [The Dual Role of Abstracting over the Irrelevant in Symbolic Explanations: Cognitive Effort vs. Understanding](https://mlsanity.com/paper/2602.03467/) (2026)

## Abstract (arXiv)

Given the recent successes of Deep Learning in AI there has been increased interest in the role and need for explanations in machine learned theories. A distinct notion in this context is that of Michie's definition of Ultra-Strong Machine Learning (USML). USML is demonstrated by a measurable increase in human performance of a task following provision to the human of a symbolic machine learned theory for task performance. A recent paper demonstrates the beneficial effect of a machine learned logic theory for a classification task, yet no existing work to our knowledge has examined the potential harmfulness of machine's involvement for human comprehension during learning. This paper investigates the explanatory effects of a machine learned theory in the context of simple two person games and proposes a framework for identifying the harmfulness of machine explanations based on the Cognitive Science literature. The approach involves a cognitive window consisting of two quantifiable bounds and it is supported by empirical evidence collected from human trials. Our quantitative and qualitative results indicate that human learning aided by a symbolic machine learned theory which satisfies a cognitive window has achieved significantly higher performance than human self learning. Results also demonstrate that human learning aided by a symbolic machine learned theory that fails to satisfy this window leads to significantly worse performance than unaided human learning.