相关论文: Extracting PAC Decision Trees from Black Box Binar…

When used in complex engineered systems, such as communication networks, artificial intelligence (AI) models should be not only as accurate as possible, but also well calibrated. A well-calibrated AI model is one that can reliably quantify…

Language Models have ushered a new age of AI gaining traction within the NLP community as well as amongst the general population. AI's ability to make predictions, generations and its applications in sensitive decision-making scenarios,…

Classical PAC generalization bounds on the prediction risk of a classifier are insufficient to provide theoretical guarantees on fairness when the goal is to learn models balancing predictive risk and fairness constraints. We propose a…

We introduce an adaptive tree search algorithm, that can find high-scoring outputs under translation models that make no assumptions about the form or structure of the search objective. This algorithm -- a deterministic variant of Monte…

Tree-based ensemble methods such as random forests, gradient-boosted trees, and Bayesianadditive regression trees have been successfully used for regression problems in many applicationsand research studies. In this paper, we study ensemble…

Black box systems for automated decision making, often based on machine learning over (big) data, map a user's features into a class or a score without exposing the reasons why. This is problematic not only for lack of transparency, but…

Medical systems in general, and patient treatment decisions and outcomes in particular, are affected by bias based on gender and other demographic elements. As language models are increasingly applied to medicine, there is a growing…

Feature attribution methods have become a staple method to disentangle the complex behavior of black box models. Despite their success, some scholars have argued that such methods suffer from a serious flaw: they do not allow a reliable…

Language models have been shown to propagate social bias through their output, particularly in the representation of gender and ethnicity. This paper investigates gender and ethnicity biases in AI-generated occupational stories.…

Explainable AI has attracted much research attention in recent years with feature attribution algorithms, which compute "feature importance" in predictions, becoming increasingly popular. However, there is little analysis of the validity of…

Ensuring trustworthiness in open-world visual recognition requires models that are interpretable, fair, and robust to distribution shifts. Yet modern vision systems are increasingly deployed as proprietary black-box APIs, exposing only…

Interpretable surrogates of black-box predictors trained on high-dimensional tabular datasets can struggle to generate comprehensible explanations in the presence of correlated variables. We propose a model-agnostic interpretable surrogate…

In recent years, XAI researchers have been formalizing proposals and developing new methods to explain black box models, with no general consensus in the community on which method to use to explain these models, with this choice being…

In recent years, automated data-driven decision-making systems have enjoyed a tremendous success in a variety of fields (e.g., to make product recommendations, or to guide the production of entertainment). More recently, these algorithms…

Bayesian averaging over classification models allows the uncertainty of classification outcomes to be evaluated, which is of crucial importance for making reliable decisions in applications such as financial in which risks have to be…

Machine learning algorithms are fundamental components of novel data-informed Artificial Intelligence architecture. In this domain, the imperative role of representative datasets is a cornerstone in shaping the trajectory of artificial…

Model selection consists in comparing several candidate models according to a metric to be optimized. The process often involves a grid search, or such, and cross-validation, which can be time consuming, as well as not providing much…

Deep models have advanced prediction in many domains, but their lack of interpretability remains a key barrier to the adoption in many real world applications. There exists a large body of work aiming to help humans understand these black…

The prevailing approach for training and evaluating paraphrase identification models is constructed as a binary classification problem: the model is given a pair of sentences, and is judged by how accurately it classifies pairs as either…

Machine learning solutions for pattern classification problems are nowadays widely deployed in society and industry. However, the lack of transparency and accountability of most accurate models often hinders their safe use. Thus, there is a…