Calibration ensures that predicted uncertainties align with observed uncertainties. While there is an extensive literature on recalibration methods for univariate probabilistic forecasts, work on calibration for multivariate forecasts is much more limited. This paper introduces a novel post-hoc recalibration approach that addresses multivariate calibration for potentially misspecified models. Our method involves constructing local mappings between vectors of marginal probability integral transform values and the space of observations, providing a flexible and model free solution applicable to continuous, discrete, and mixed responses. We present two versions of our approach: one uses K-nearest neighbors, and the other uses normalizing flows. Each method has its own strengths in different situations. We demonstrate the effectiveness of our approach on two real data applications: recalibrating a deep neural network's currency exchange rate forecast and improving a regression model for childhood malnutrition in India for which the multivariate response has both discrete and continuous components.

The XOR problem has traditionally been used to illustrate the limitations of single-layer networks since Minsky and Papert's seminal work [8], which even contributed to the first AI Winter [12]. It has traditionally required at least one hidden layer to solve, making it a litmus test for network complexity. Trivially, any function, no matter how complex, can be learned in a single layer by just using itself as the activation function, and that says nothing about its general applicability and usefulness. Here, however, we reveal this ability in a simple, general and well-established activation function. This study demonstrates how using the Parametric Rectified Linear Unit (PReLU) activation [4] overcomes these limitations, effectively solving the XOR problem without additional layers. This ability has significant implications for neural network design and efficiency, potentially leading to simpler architectures for complex problems. On another front, recent advancements in neuroscience have revealed that individual human neocortical pyramidal neurons can learn to compute the XOR function [3]. This discovery has inspired new artificial neuron models and activation functions that aim to bridge the gap between biological and artificial neurons [9]. Albeit not producing the same activation curves as the ones found in biological neurons, the PReLU activation matches their representational power, at least regarding the XOR function.

As the manufacturing industry shifts from mass production to mass customization, there is a growing emphasis on adopting agile, resilient, and human-centric methodologies in line with the directives of Industry 5.0. Central to this transformation is the deployment of digital twins, a technology that digitally replicates manufacturing assets to enable enhanced process optimization, predictive maintenance, synthetic data generation, and accelerated customization and prototyping. This chapter delves into the technologies underpinning the creation of digital twins specifically tailored to agile manufacturing scenarios within the realm of robotic automation. It explores the transfer of trained policies and process optimizations from simulated settings to real-world applications through advanced techniques such as domain randomization, domain adaptation, curriculum learning, and model-based system identification. The chapter also examines various industrial manufacturing automation scenarios, including bin-picking, part inspection, and product assembly, under Sim2Real conditions. The performance of digital twin technologies in these scenarios is evaluated using practical metrics including data latency, adaptation rate, simulation fidelity among others reported, providing a comprehensive assessment of their efficacy and potential impact on modern manufacturing processes.

In the era of big data, ensuring the quality of datasets has become increasingly crucial across various domains. We propose a comprehensive framework designed to automatically assess and rectify data quality issues in any given dataset, regardless of its specific content, focusing on both textual and numerical data. Our primary objective is to address three fundamental types of defects: absence, redundancy, and incoherence. At the heart of our approach lies a rigorous demand for both explainability and interpretability, ensuring that the rationale behind the identification and correction of data anomalies is transparent and understandable. To achieve this, we adopt a hybrid approach that integrates statistical methods with machine learning algorithms. Indeed, by leveraging statistical techniques alongside machine learning, we strike a balance between accuracy and explainability, enabling users to trust and comprehend the assessment process. Acknowledging the challenges associated with automating the data quality assessment process, particularly in terms of time efficiency and accuracy, we adopt a pragmatic strategy, employing resource-intensive algorithms only when necessary, while favoring simpler, more efficient solutions whenever possible. Through a practical analysis conducted on a publicly provided dataset, we illustrate the challenges that arise when trying to enhance data quality while keeping explainability. We demonstrate the effectiveness of our approach in detecting and rectifying missing values, duplicates and typographical errors as well as the challenges remaining to be addressed to achieve similar accuracy on statistical outliers and logic errors under the constraints set in our work.

Wildfires pose a significant natural disaster risk to populations and contribute to accelerated climate change. As wildfires are also affected by climate change, extreme wildfires are becoming increasingly frequent. Although they occur less frequently globally than those sparked by human activities, lightning-ignited wildfires play a substantial role in carbon emissions and account for the majority of burned areas in certain regions. While existing computational models, especially those based on machine learning, aim to predict lightning-ignited wildfires, they are typically tailored to specific regions with unique characteristics, limiting their global applicability. In this study, we present machine learning models designed to characterize and predict lightning-ignited wildfires on a global scale. Our approach involves classifying lightning-ignited versus anthropogenic wildfires, and estimating with high accuracy the probability of lightning to ignite a fire based on a wide spectrum of factors such as meteorological conditions and vegetation. Utilizing these models, we analyze seasonal and spatial trends in lightning-ignited wildfires shedding light on the impact of climate change on this phenomenon. We analyze the influence of various features on the models using eXplainable Artificial Intelligence (XAI) frameworks. Our findings highlight significant global differences between anthropogenic and lightning-ignited wildfires. Moreover, we demonstrate that, even over a short time span of less than a decade, climate changes have steadily increased the global risk of lightning-ignited wildfires. This distinction underscores the imperative need for dedicated predictive models and fire weather indices tailored specifically to each type of wildfire.

Large Language Model (LLM)-based recommendation systems provide more comprehensive recommendations than traditional systems by deeply analyzing content and user behavior. However, these systems often exhibit biases, favoring mainstream content while marginalizing non-traditional options due to skewed training data. This study investigates the intricate relationship between bias and LLM-based recommendation systems, with a focus on music, song, and book recommendations across diverse demographic and cultural groups. Through a comprehensive analysis conducted over different LLM-models, this paper evaluates the impact of bias on recommendation outcomes. Our findings reveal that bias is so deeply ingrained within these systems that even a simpler intervention like prompt engineering can significantly reduce bias, underscoring the pervasive nature of the issue. Moreover, factors like intersecting identities and contextual information, such as socioeconomic status, further amplify these biases, demonstrating the complexity and depth of the challenges faced in creating fair recommendations across different groups.

Predicting high-dimensional or extreme multilabels, such as in medical coding, requires both accuracy and interpretability. Existing works often rely on local interpretability methods, failing to provide comprehensive explanations of the overall mechanism behind each label prediction within a multilabel set. We propose a mechanistic interpretability module called DIctionary Label Attention (\method) that disentangles uninterpretable dense embeddings into a sparse embedding space, where each nonzero element (a dictionary feature) represents a globally learned medical concept. Through human evaluations, we show that our sparse embeddings are more human understandable than its dense counterparts by at least 50 percent. Our automated dictionary feature identification pipeline, leveraging large language models (LLMs), uncovers thousands of learned medical concepts by examining and summarizing the highest activating tokens for each dictionary feature. We represent the relationships between dictionary features and medical codes through a sparse interpretable matrix, enhancing the mechanistic and global understanding of the model's predictions while maintaining competitive performance and scalability without extensive human annotation.

Dialogue summarization aims to provide a concise and coherent summary of conversations between multiple speakers. While recent advancements in language models have enhanced this process, summarizing dialogues accurately and faithfully remains challenging due to the need to understand speaker interactions and capture relevant information. Indeed, abstractive models used for dialog summarization may generate summaries that contain inconsistencies. We suggest using the semantic information proposed for performing Spoken Language Understanding (SLU) in human-machine dialogue systems for goal-oriented human-human dialogues to obtain a more semantically faithful summary regarding the task. This study introduces three key contributions: First, we propose an exploration of how incorporating task-related information can enhance the summarization process, leading to more semantically accurate summaries. Then, we introduce a new evaluation criterion based on task semantics. Finally, we propose a new dataset version with increased annotated data standardized for research on task-oriented dialogue summarization. The study evaluates these methods using the DECODA corpus, a collection of French spoken dialogues from a call center. Results show that integrating models with task-related information improves summary accuracy, even with varying word error rates.

AI fairness measurements, including tests for equal treatment, often take the form of disaggregated evaluations of AI systems. Such measurements are an important part of Responsible AI operations. These measurements compare system performance across demographic groups or sub-populations and typically require member-level demographic signals such as gender, race, ethnicity, and location. However, sensitive member-level demographic attributes like race and ethnicity can be challenging to obtain and use due to platform choices, legal constraints, and cultural norms. In this paper, we focus on the task of enabling AI fairness measurements on race/ethnicity for \emph{U.S. LinkedIn members} in a privacy-preserving manner. We present the Privacy-Preserving Probabilistic Race/Ethnicity Estimation (PPRE) method for performing this task. PPRE combines the Bayesian Improved Surname Geocoding (BISG) model, a sparse LinkedIn survey sample of self-reported demographics, and privacy-enhancing technologies like secure two-party computation and differential privacy to enable meaningful fairness measurements while preserving member privacy. We provide details of the PPRE method and its privacy guarantees. We then illustrate sample measurement operations. We conclude with a review of open research and engineering challenges for expanding our privacy-preserving fairness measurement capabilities.

Debiasing is often challenging due to computational costs, data constraints, and potential degradation of multi-task language capabilities. This work introduces a novel approach utilizing ChatGPT to generate synthetic training data, aiming to enhance the debiasing of LLMs. We propose two strategies: Targeted Prompting, which provides effective debiasing for known biases but necessitates prior specification of bias in question; and General Prompting, which, while slightly less effective, offers debiasing across various categories. We leverage resource-efficient LLM debiasing using adapter tuning and compare the effectiveness of our synthetic data to existing debiasing datasets. Our results reveal that: (1) ChatGPT can efficiently produce high-quality training data for debiasing other LLMs; (2) data produced via our approach surpasses existing datasets in debiasing performance while also preserving internal knowledge of a pre-trained LLM; and (3) synthetic data exhibits generalizability across categories, effectively mitigating various biases, including intersectional ones. These findings underscore the potential of synthetic data in advancing the fairness of LLMs with minimal retraining cost.