Related papers: Accountable Error Characterization
Understanding why machine learning models behave the way they do empowers both system designers and end-users in many ways: in model selection, feature engineering, in order to trust and act upon the predictions, and in more intuitive user…
We propose a general model explanation system (MES) for "explaining" the output of black box classifiers. This paper describes extensions to Turner (2015), which is referred to frequently in the text. We use the motivating example of a…
Reliably predicting potential failure risks of machine learning (ML) systems when deployed with production data is a crucial aspect of trustworthy AI. This paper introduces Risk Advisor, a novel post-hoc meta-learner for estimating failure…
Machine learning algorithms in socially sensitive domains (e.g., credit decisions) often focus on equalizing predictive outcomes. However, satisfying these metrics does not guarantee that models use the same reasoning for different groups.…
Deep neural network-based classifiers are prone to errors when processing adversarial examples (AEs). AEs are minimally perturbed input data undetectable to humans posing significant risks to security-dependent applications. Hence,…
In this paper, we investigate an artificial-intelligence (AI) driven approach to design error correction codes (ECC). Classic error correction code was designed upon coding theory that typically defines code properties (e.g., hamming…
We introduce Matched Machine Learning, a framework that combines the flexibility of machine learning black boxes with the interpretability of matching, a longstanding tool in observational causal inference. Interpretability is paramount in…
Benchmarking models is a key factor for the rapid progress in machine learning (ML) research. Thus, further progress depends on improving benchmarking metrics. A standard metric to measure the behavioral alignment between ML models and…
Modern predictive analytics underpinned by machine learning techniques has become a key enabler to the automation of data-driven decision making. In the context of business process management, predictive analytics has been applied to making…
Evaluating machine learning models is crucial not only for determining their technical accuracy but also for assessing their potential societal implications. While the potential for low-sample-size bias in algorithms is well known, we…
Causal machine learning tools are beginning to see use in real-world policy evaluation tasks to flexibly estimate treatment effects. One issue with these methods is that the machine learning models used are generally black boxes, i.e.,…
The widespread use of machine learning in credit scoring has brought significant advancements in risk assessment and decision-making. However, it has also raised concerns about potential biases, discrimination, and lack of transparency in…
Foundation models often generate unreliable answers, while heuristic uncertainty estimators fail to fully distinguish correct from incorrect outputs, causing users to accept erroneous answers without any statistical guarantee. We address…
Most AI systems are black boxes generating reasonable outputs for given inputs. Some domains, however, have explainability and trustworthiness requirements that cannot be directly met by these approaches. Various methods have therefore been…
Existing deep active learning algorithms achieve impressive sampling efficiency on natural language processing tasks. However, they exhibit several weaknesses in practice, including (a) inability to use uncertainty sampling with black-box…
This research describes the initial effort of building a prediction model for defects in system testing carried out by an independent testing team. The motivation to have such defect prediction model is to serve as early quality indicator…
Modern AI systems are typically developed through multiple stages-pretraining, fine-tuning rounds, and subsequent adaptation or alignment, where each stage builds on the previous ones and updates the model in distinct ways. This raises a…
Given a deep neural network image classification model that we treat as a black box, and an unlabeled evaluation dataset, we develop an efficient strategy by which the classifier can be evaluated. Randomly sampling and labeling instances…
The digitalization of credit scoring has become essential for financial institutions and commercial banks, especially in the era of digital transformation. Machine learning techniques are commonly used to evaluate customers'…
Artificial intelligence methods are being increasingly applied across various domains, but their often opaque nature has raised concerns about accountability and trust. In response, the field of explainable AI (XAI) has emerged to address…