Related papers: Auditing Local Explanations is Hard
Every digital process needs to consume some data in order to work properly. It is very common for applications to use some external data in their processes, getting them by sources such as external APIs. Therefore, trusting the received…
Smart contracts are decentralized applications built atop blockchains like Ethereum. Recent research has shown that large language models (LLMs) have potential in auditing smart contracts, but the state-of-the-art indicates that even GPT-4…
Patients increasingly rely on online reviews when choosing healthcare providers, yet the sheer volume of these reviews can hinder effective decision-making. This paper summarises a mixed-methods study aimed at evaluating a proposed…
Search engines that present users with a ranked list of search results are a fundamental technology for providing public access to information. Evaluations of such systems are typically conducted by domain experts and focus on model-centric…
As artificial intelligence (AI) becomes more prevalent there is a growing demand from regulators to accompany decisions made by such systems with explanations. However, a persistent gap exists between the need to execute a meaningful right…
As machine learning becomes an important part of many real world applications affecting human lives, new requirements, besides high predictive accuracy, become important. One important requirement is transparency, which has been associated…
There exist several methods that aim to address the crucial task of understanding the behaviour of AI/ML models. Arguably, the most popular among them are local explanations that focus on investigating model behaviour for individual…
Automated hiring systems are among the fastest-developing of all high-stakes AI systems. Among these are algorithmic personality tests that use insights from psychometric testing, and promise to surface personality traits indicative of…
For applications of machine learning in critical decisions, explainability is a primary concern, and often a regulatory requirement. Local linear methods for generating explanations, such as LIME and SHAP, have been criticized for being…
Recent work in explanation generation for decision making agents has looked at how unexplained behavior of autonomous systems can be understood in terms of differences in the model of the system and the human's understanding of the same,…
Privacy leakage in AI-based decision processes poses significant risks, particularly when sensitive information can be inferred. We propose a formal framework to audit privacy leakage using abductive explanations, which identifies minimal…
As Artificial Intelligence (AI) is increasingly used in areas that significantly impact human lives, concerns about fairness and transparency have grown, especially regarding their impact on protected groups. Recently, the intersection of…
The fast spreading adoption of machine learning (ML) by companies across industries poses significant regulatory challenges. One such challenge is scalability: how can regulatory bodies efficiently audit these ML models, ensuring that they…
Machine learning systems increasingly make life-changing decisions about individuals, such as loan approvals, hiring, and cheating detection, raising a pressing question: how can individuals respond to negative decisions made by these…
Explainability, i.e. the ability of a system to explain its behavior to users, has become an important quality of software-intensive systems. Recent work has focused on methods for generating explanations for various algorithmic paradigms…
We investigate whether large language models (LLMs) can generate effective, user-facing explanations from a mathematically interpretable recommendation model. The model is based on constrained matrix factorization, where user types are…
Existing work on fairness typically focuses on making known machine learning algorithms fairer. Fair variants of classification, clustering, outlier detection and other styles of algorithms exist. However, an understudied area is the topic…
Large language models have exhibited impressive performance across a broad range of downstream tasks in natural language processing. However, how a language model predicts the next token and generates content is not generally understandable…
It is a mystery which input features contribute to a neural network's output. Various explanation (feature attribution) methods are proposed in the literature to shed light on the problem. One peculiar observation is that these explanations…
In this paper we argue that, to its detriment, transparency research overlooks many foundational concepts of artificial intelligence. As an illustrating example we focus on uncertainty quantification in the context of counterfactual…