24 accepted papers
This paper introduces the Shepherd Test, a new conceptual test for assessing the moral and relational dimensions of superintelligent artificial agents. The test is inspired by human interactions with animals, where ethical considerations about care, manipulation, and consumption arise in contexts of
Developing value-aligned agents is a complex undertaking and an ongoing challenge in the field of AI. Indeed, designing Large Language Models (LLMs) that can balance multiple possibly conflicting moral values based on the context is a problem of paramount importance. In this paper, we propose a syst…
Building pluralistic AI requires designing models that are able to be shaped to represent a wide range of value systems and cultures. Achieving this requires first being able to evaluate the degree to which a given model is capable of reflecting various personas. To this end, we propose a benchmark…
The deployment of language models in real-world applications exposes users to various risks, including hallucinations and harmful or unethical content. These challenges highlight the urgent need for robust safeguards to ensure safe and responsible AI. To address this, we introduce Granite Guardian,…
In contemporary society, the integration of artificial intelligence (AI) systems into various aspects of daily life raises significant ethical concerns. One critical aspect is to ensure that AI systems align with the moral values of the endusers. To that end, we introduce the Contextual Moral Value…
Discontinuation rates vary by family planning method and across socio-economic contexts. Understanding these variations and their causes is paramount for developing and implementing policies aimed at curbing discontinuation rates. Randomized controlled trials (RCTs) are ideal for obtaining this info…
Aligning large language models (LLMs) to value systems has emerged as a significant area of research within the fields of AI and NLP. Currently, this alignment process relies on the availability of high-quality supervised and preference data, which can be both time-consuming and expensive to curate…
We introduce equi-tuning, a novel fine-tuning method that transforms (potentially non-equivariant) pretrained models into group equivariant models while incurring minimum L_2 loss between the feature representations of the pretrained and the equivariant models. Large pretrained models can be equi-tu…
The use of machine learning models in consequential decision making often exacerbates societal inequity, in particular yielding disparate impact on members of marginalized groups defined by race and gender. The area under the ROC curve (AUC) is widely used to evaluate the performance of a scoring fu…
Invariant risk minimization (IRM) has received increasing attention as a way to acquire environment-agnostic data representations and predictions, and also a principled solution for preventing spurious correlations from being learned and improving models’ out-of-distribution generalization. Yet, rec…
In consequential decision-making applications, mitigating unwanted biases in machine learning models that yield systematic disadvantage to members of groups delineated by sensitive attributes such as race and gender is one key intervention to strive for equity. Focusing on demographic parity and equ…
Interpretable and explainable machine learning has seen a recent surge of interest. We focus on safety as a key motivation behind the surge and make the relationship between interpretability and safety more quantitative. Toward assessing safety, we introduce the concept of *maximum deviation* via an…
In recent years there has been a considerable amount of research on local post hoc explanations for neural networks. However, work on building interpretable neural architectures has been relatively sparse. In this paper, we present a novel neural architecture, CoFrNet, inspired by the form of contin…
Recently, invariant risk minimization (IRM) was proposed as a promising solution to address out-of-distribution (OOD) generalization. However, it is unclear when IRM should be preferred over the widely-employed empirical risk minimization (ERM) framework. In this work, we analyze both these framewor…
Inferring causal individual treatment effect (ITE) from observational data is a challenging problem whose difficulty is exacerbated by the presence of treatment assignment bias. In this work, we propose a new way to estimate the ITE using the domain generalization framework of invariant risk minimiz…
Improving maternal, newborn, and child health (MNCH) outcomes is a critical target for global sustainable development. Our research is centered on building predictive models, evaluating their interpretability, and generating actionable insights about the markers (features) and triggers (events) asso…
We investigate the effect of variational autoencoder (VAE) based data anonymization and its ability to preserve anomalous subgroup properties. We present a Utility Guaranteed Deep Privacy (UGDP) system which casts existing anomalous pattern detection methods as a new utility measure for data synthes…
Whereas previous post-processing approaches for increasing the fairness of predictions of biased classifiers address only group fairness, we propose a method for increasing both individual and group fairness. Our novel framework includes an individual bias detector used to prioritize data samples in…
In previous work, we proposed a scalable multi-party verification scheme for expensive iterative computations on a Blockchain substrate by appropriate storage and endorsement of frames of iterates. In this work, we extend the framework to verify sets of complete computations with different unordered…
Non-discrimination is a recognized objective in algorithmic decision making. In this paper, we introduce a novel probabilistic formulation of data pre-processing for reducing discrimination. We propose a convex optimization for learning a data transformation with three goals: controlling discriminat…
Recommendation for e-commerce with a mix of durable and nondurable goods has characteristics that distinguish it from the well-studied media recommendation problem. The demand for items is a combined effect of form utility and time utility, i.e., a product must both be intrinsically appealing to a c…
In our previous work we have presented an approach to learn interpretable classification rules using a Boolean compressed sensing formulation. Our approach uses a linear programming (LP) relaxation and allows us to find interpretable (sparse) classification rules that achieve good generalization acc…
Topological signal processing, especially persistent homology, is a growing field of study for analyzing sets of data points that has been heretofore applied to unlabeled data. In this work, we consider the case of labeled data and examine the topology of the decision boundary separating different l…
In hypothesis testing, the phenomenon of label noise, in which hypothesis labels are switched at random, contaminates the likelihood functions. In this paper, we develop a new method to determine the decision rule when we do not have knowledge of the uncontaminated likelihoods and contamination prob…