Related papers: Enforcing Consistency and Fairness in Multi-level …

Transformer-based Large Language Models (LLMs) have demonstrated powerful in-context learning capabilities. However, their predictions can be disrupted by factually correct context, a phenomenon known as context hijacking, revealing a…

Conformal prediction methods provide statistically rigorous marginal coverage guarantees for machine learning models, but such guarantees fail to account for algorithmic biases, thereby undermining fairness and trust. This paper introduces…

The deployment of Large Language Models (LLMs) in high-stakes medical settings poses a critical AI alignment challenge, as models can inherit and amplify societal biases, leading to significant disparities. Existing fairness evaluation…

Employing Large Language Models (LLM) in various downstream applications such as classification is crucial, especially for smaller companies lacking the expertise and resources required for fine-tuning a model. Fairness in LLMs helps ensure…

Fairness research in machine learning often centers on ensuring equitable performance of individual models. However, real-world recommendation systems are built on multiple models and even multiple stages, from candidate retrieval to…

In this study we want to connect our previously proposed context-relevant topographical maps with the deep learning community. Our architecture is a classifier with hidden layers that are hierarchical two-dimensional topographical maps.…

The organization of latent token representations plays a crucial role in determining the stability, generalization, and contextual consistency of language models, yet conventional approaches to embedding refinement often rely on parameter…

Most classification models treat all misclassifications equally. However, different classes may be related, and these hierarchical relationships must be considered in some classification problems. These problems can be addressed by using…

Introduced as a notion of algorithmic fairness, multicalibration has proved to be a powerful and versatile concept with implications far beyond its original intent. This stringent notion -- that predictions be well-calibrated across a rich…

The advent of Large Language Models (LLMs) has provided unprecedented capabilities for analyzing unstructured text data. However, deploying these models as reliable, robust, and scalable classifiers in production environments presents…

Algorithmic decision making systems are ubiquitous across a wide variety of online as well as offline services. These systems rely on complex learning methods and vast amounts of data to optimize the service functionality, satisfaction of…

Classification aids software development activities by organizing requirements in classes for easier access and retrieval. The majority of requirements classification research has, so far, focused on binary or multi-class classification.…

As machine learning (ML) based systems are adopted in domains such as law enforcement, criminal justice, finance, hiring and admissions, ensuring the fairness of ML aided decision-making is becoming increasingly important. In this paper, we…

With the society's growing adoption of machine learning (ML) and deep learning (DL) for various intelligent solutions, it becomes increasingly imperative to standardize a common set of measures for ML/DL models with large scale open…

Classification, a heavily-studied data-driven machine learning task, drives an increasing number of prediction systems involving critical human decisions such as loan approval and criminal risk assessment. However, classifiers often…

Multi-label classification (MLC) is an ML task of predictive modeling in which a data instance can simultaneously belong to multiple classes. MLC is increasingly gaining interest in different application domains such as text mining,…

Classification algorithms in machine learning often assume a flat label space. However, most real world data have dependencies between the labels, which can often be captured by using a hierarchy. Utilizing this relation can help develop a…

Fair machine learning (ML) methods help identify and mitigate the risk that algorithms encode or automate social injustices. Algorithmic approaches alone cannot resolve structural inequalities, but they can support socio-technical decision…

This work proposes a novel approach to the deep hierarchical classification task, i.e., the problem of classifying data according to multiple labels organized in a rigid parent-child structure. It consists in a multi-output deep neural…

Fairness has become increasingly pivotal in facial recognition. Without bias mitigation, deploying unfair AI would harm the interest of the underprivileged population. In this paper, we observe that though the higher accuracy that features…