XAI Today

Gender Controlled Data Sets for XAI Research

The paper “GECOBench: A Gender-Controlled Text Dataset and Benchmark for Quantifying Biases in Explanations” introduces a novel dataset, GECO, to evaluate biases in AI explanations, specifically focusing on gender. The authors constructed the dataset with sentence pairs that differ only in gendered pronouns or names, enabling a controlled analysis of gender biases in AI-generated text. GECOBench, an accompanying benchmark, assesses different explainable AI (XAI) methods by measuring their ability to detect and mitigate biases within this context.

Explaining Random Forests with Representative Trees

The paper “Can’t see the forest for the trees: Analyzing groves to explain random forests” explores a novel take on model-specific explanations, as outlined in my own research (e.g. you can look at “CHIRPS: Explaining random forest classification” as a reference). This new paper by Szepannek and von Holt seeks to make Random Forests (RF) more interpretable. RF are notoriously hard to explain due to their complexity and these novel methods works well for both classification and regression, which is a very useful extension to the field.

Combatting Fake News With XAI

With all the unhinged hype over ChatGPT stealing everyone’s jobs and AI taking over the world, it’s great to see postiive use cases for Machine Learning (ML) technologies. As usual, eXplainable Artificial Intelligence (XAI) has something to contribute to the ethical landscape of fairness and transparency. In this recent news article we see a concerted attempt to combat fake news with XAI and a pretty sophisticated tech stack. With the rise of social media and other online platforms, the spread of fake news has become a major problem. Fake news is defined as news stories that are intentionally false and designed to mislead readers. It is often spread through social media and can have serious consequences, such as influencing public opinion and even swaying elections.

Explaining Random Forests with Boolean Satisfiability

The paper “On Explaining Random Forests with SAT” uses Boolean satisfiability (SAT) methods to provide a formal framework for generating explanations of Random Forest (RF) predictions. A key result in the paper is that abductive explanations (AXp) and contrastive explanations (CXp) can be derived by encoding the RF’s decision paths into propositional logic. Encoding a decision path as propositional logic, is an entirely reasoned approach and quite straightforward, as I showed in my paper CHIRPS: Explaining random forest classification. The decision paths of an RF model can be transformed into a Boolean formula in Conjunctive Normal Form (CNF). For example, each decision tree in the forest is represented as a set of clauses. Following the paths for a single example prediction essentially carves out a region of the feature space with a set of step functions, resulting in a sub-region that must return the target response. When the clauses of this step functions set correspond to a subset of the features, a change in the remaining feature inputs has no effect on the model prediction. This subset is a prime implicant (PI) explanation.

Counterfactual Explanations Help Identify Sources of Bias

By the end of 2020, the topic of eXplainable Artificial Intelligence (XAI) has become quite mainstream. One important developlment is counterfactual explanations, which (among other benefits) can to identify and reduce bias in machine learning models. Counterfactual explanations provide insights by showing how minimal changes in input features can alter model predictions. This approach has been crucial in exposing biased behavior, especially in sensitive applications like credit scoring or hiring. By identifying how protected attributes (e.g., gender or race) affect outcomes, practitioners could better address and mitigate unfair biases in AI systems (Verma et al., 2020).