# CAUSAL CONCEPT-BASED EXPLANATIONS

DevFeed: [CAUSAL CONCEPT-BASED EXPLANATIONS](<https://devfeed.tech/articles/causal-concept-based-explanations-26296.md>)

Original publisher: [Read original article](<https://medium.com/feedzaitech/causal-concept-based-explanations-8e0b4c8c86ac?source=rss----e11168e7fe6b---4>)

Author: Jacopo Bono

Published: 2025-10-03T13:09:07Z

Content type: article

Language: en

Sources: [Feedzai](<https://devfeed.tech/sources/feedzai.md>)

Topics: [Machine Learning & Artificial Intelligence](<https://devfeed.tech/topics/machine-learning-artificial-intelligence.md>), [Machine learning](<https://devfeed.tech/topics/machine-learning.md>), [AI Development](<https://devfeed.tech/topics/ai-development.md>)

Tags: [ai](<https://devfeed.tech/tags/ai.md>), [blog-post](<https://devfeed.tech/tags/blog-post.md>), [causality](<https://devfeed.tech/tags/causality.md>), [concept-learning](<https://devfeed.tech/tags/concept-learning.md>), [deep-learning](<https://devfeed.tech/tags/deep-learning.md>), [explainability](<https://devfeed.tech/tags/explainability.md>), [machine-learning](<https://devfeed.tech/tags/machine-learning.md>), [research](<https://devfeed.tech/tags/research.md>), [technical](<https://devfeed.tech/tags/technical.md>)

## AI overview

The article introduces causal concept-based explanations for machine learning models. It argues that existing feature-attribution explanations can be too complex for humans and usually do not support reasoning about hypothetical alternatives. The proposed method aims to provide more human-understandable, reasoning-oriented explanations, with technical details deferred to a publication at the 2024 CLeaR conference.

## Source excerpt

Introduction Over the years, we have evolved from using simple, often rule-based algorithms to sophisticated machine learning models. These models are incredibly good at finding patterns in large datasets, but due to their complexity it is frequently challenging for a human to understand why a certain input leads to its respective output. This is especially problematic in areas where high-stakes decisions are being made and where human-AI collaboration is critical. This is why model explainability has gained traction in recent years. The aim of explainability methods is to shed light on what properties of the data contribute to a machine learning model's output. Ideally, such explanations should be similar to how a human would explain its decisions to a peer. In particular, humans make use of high-level concepts that are easy to grasp for other people. For example, a human would explain, "there was a sudden burst of transactions in a short time" as opposed to, "the average delta time feature is much smaller in a recent short time-window compared to a long time-window, and the count of transactions feature increased substantially in the same recent time-window." Moreover, when explaining choices and decisions, humans are free to reflect on these decisions by reasoning about hypothetical alternatives. For example, we could ask, "if this email address would be considered suspicious, would I trust this request?" Current explainability methods fail to incorporate both properties: the explanations are often much more complex than typical concepts humans would use; and they don't allow for reasoning. As a result, these limitations impede the usefulness of current explainability methods in many practical applications. In this blog post, we will describe a new explainability method that addresses these issues. We'll try to refrain from discussing too many technical details and focus on the intuition behind the method, but readers interested in the technical justifications ar