Large language models (LLMs) have demonstrated strong results on a range of NLP tasks. Typically, outputs are obtained via autoregressive sampling from the LLM's underlying distribution. Building on prior work on Minimum Bayes Risk decoding, we show that this inference strategy can be suboptimal for a range of regression and scoring tasks, and associated evaluation metrics. As a remedy, we propose metric aware LLM inference: a decision theoretic approach optimizing for custom regression and scoring metrics at inference time. We report improvements over baselines on academic benchmarks and publicly available models.

Earthwork-related locations (ERLs), such as construction sites, earth dumping ground, and concrete mixing stations, are major sources of urban dust pollution (particulate matters). The effective management of ERLs is crucial and requires timely and efficient tracking of these locations throughout the city. This work aims to identify and classify urban ERLs using GPS trajectory data of over 16,000 construction waste hauling trucks (CWHTs), as well as 58 urban features encompassing geographic, land cover, POI and transport dimensions. We compare several machine learning models and examine the impact of various spatial-temporal features on classification performance using real-world data in Chengdu, China. The results demonstrate that 77.8% classification accuracy can be achieved with a limited number of features. This classification framework was implemented in the Alpha MAPS system in Chengdu, which has successfully identified 724 construction cites/earth dumping ground, 48 concrete mixing stations, and 80 truck parking locations in the city during December 2023, which has enabled local authority to effectively manage urban dust pollution at low personnel costs.

FOG affects between 50% and 80% of people with PD (Weiss et al., 2015), and its presence is associated with an increased risk of falls, affecting the quality of life (Moore et al., 2007). When a FOG episode appears, PD patients can present variability in the gait pattern, with a reduction in step length, shuffling steps, trembling of the legs, and total akinesia with a loss of movement of the limbs or trunk (Okuma, 2014). FOG episodes can have a duration of a few seconds (1 second or less for very short episodes and more than 5 seconds for long episodes) and appear more frequently during typical daily-life conditions than during straight walking assessments in clinical and laboratory settings (Okuma, 2014; Nonnekes et al., 2015). FOG assessment involves the identification of the presence (or absence) of FOG episodes and also aims to identify their severity (Mancini et al., 2019). Assessing FOG in the clinical practice is difficult because of the lack of an optimal freezing score, and difficulties related to the clinical assessment often performed on conditions that hinder the appearance of FOG events during evaluation; for example, the assessment is usually made in the ON state, while FOG occurs more often in OFF state (Schaafsma et al., 2003; Mancini et al., 2021). Although the clinical assessment provides relevant indicators for the characterization of FOG, the conditions whereby these are performed do not accurately represent the severity of FOG in daily life (Rahman et al., 2008; Snijders et al., 2008), such as the patients' homes, where FOG events tend to occur more frequently (Nieuwboer et al., 1998).

Multi-task learning (MTL) aims to improve estimation and prediction performance by sharing common information among related tasks. One natural assumption in MTL is that tasks are classified into clusters based on their characteristics. However, existing MTL methods based on this assumption often ignore outlier tasks that have large task-specific components or no relation to other tasks. To address this issue, we propose a novel MTL method called Multi-Task Learning via Robust Regularized Clustering (MTLRRC). MTLRRC incorporates robust regularization terms inspired by robust convex clustering, which is further extended to handle non-convex and group-sparse penalties. The extension allows MTLRRC to simultaneously perform robust task clustering and outlier task detection. The connection between the extended robust clustering and the multivariate M-estimator is also established. This provides an interpretation of the robustness of MTLRRC against outlier tasks. An efficient algorithm based on a modified alternating direction method of multipliers is developed for the estimation of the parameters. The effectiveness of MTLRRC is demonstrated through simulation studies and application to real data.

Misogyny is often expressed through figurative language. Some neutral words can assume a negative connotation when functioning as pejorative epithets. Disambiguating the meaning of such terms might help the detection of misogyny. In order to address such task, we present PejorativITy, a novel corpus of 1,200 manually annotated Italian tweets for pejorative language at the word level and misogyny at the sentence level. We evaluate the impact of injecting information about disambiguated words into a model targeting misogyny detection. In particular, we explore two different approaches for injection: concatenation of pejorative information and substitution of ambiguous words with univocal terms. Our experimental results, both on our corpus and on two popular benchmarks on Italian tweets, show that both approaches lead to a major classification improvement, indicating that word sense disambiguation is a promising preliminary step for misogyny detection. Furthermore, we investigate LLMs' understanding of pejorative epithets by means of contextual word embeddings analysis and prompting.

Generative image models have emerged as a promising technology to produce realistic images. Despite potential benefits, concerns grow about its misuse, particularly in generating deceptive images that could raise significant ethical, legal, and societal issues. Consequently, there is growing demand to empower users to effectively discern and comprehend patterns of AI-generated images. To this end, we developed ASAP, an interactive visualization system that automatically extracts distinct patterns of AI-generated images and allows users to interactively explore them via various views. To uncover fake patterns, ASAP introduces a novel image encoder, adapted from CLIP, which transforms images into compact "distilled" representations, enriched with information for differentiating authentic and fake images. These representations generate gradients that propagate back to the attention maps of CLIP's transformer block. This process quantifies the relative importance of each pixel to image authenticity or fakeness, exposing key deceptive patterns. ASAP enables the at scale interactive analysis of these patterns through multiple, coordinated visualizations. This includes a representation overview with innovative cell glyphs to aid in the exploration and qualitative evaluation of fake patterns across a vast array of images, as well as a pattern view that displays authenticity-indicating patterns in images and quantifies their impact. ASAP supports the analysis of cutting-edge generative models with the latest architectures, including GAN-based models like proGAN and diffusion models like the latent diffusion model. We demonstrate ASAP's usefulness through two usage scenarios using multiple fake image detection benchmark datasets, revealing its ability to identify and understand hidden patterns in AI-generated images, especially in detecting fake human faces produced by diffusion-based techniques.

We explore the application of machine learning algorithms to predict the suitability of Russet potato clones for advancement in breeding trials. Leveraging data from manually collected trials in the state of Oregon, we investigate the potential of a wide variety of state-of-the-art binary classification models. We conduct a comprehensive analysis of the dataset that includes preprocessing, feature engineering, and imputation to address missing values. We focus on several key metrics such as accuracy, F1-score, and Matthews correlation coefficient (MCC) for model evaluation. The top-performing models, namely the multi-layer perceptron (MLPC), histogram-based gradient boosting classifier (HGBC), and a support vector machine (SVC), demonstrate consistent and significant results. Variable selection further enhances model performance and identifies influential features in predicting trial outcomes. The findings emphasize the potential of machine learning in streamlining the selection process for potato varieties, offering benefits such as increased efficiency, substantial cost savings, and judicious resource utilization. Our study contributes insights into precision agriculture and showcases the relevance of advanced technologies for informed decision-making in breeding programs.

Language Models (LMs) have shown promising performance in natural language generation. However, as LMs often generate incorrect or hallucinated responses, it is crucial to correctly quantify their uncertainty in responding to given inputs. In addition to verbalized confidence elicited via prompting, many uncertainty measures ($e.g.$, semantic entropy and affinity-graph-based measures) have been proposed. However, these measures can differ greatly, and it is unclear how to compare them, partly because they take values over different ranges ($e.g.$, $[0,\infty)$ or $[0,1]$). In this work, we address this issue by developing a novel and practical framework, termed $Rank$-$Calibration$, to assess uncertainty and confidence measures for LMs. Our key tenet is that higher uncertainty (or lower confidence) should imply lower generation quality, on average. Rank-calibration quantifies deviations from this ideal relationship in a principled manner, without requiring ad hoc binary thresholding of the correctness score ($e.g.$, ROUGE or METEOR). The broad applicability and the granular interpretability of our methods are demonstrated empirically.

We propose a machine learning pipeline for forensic shoeprint pattern matching that improves on the accuracy and generalisability of existing methods. We extract 2D coordinates from shoeprint scans using edge detection and align the two shoeprints with iterative closest point (ICP). We then extract similarity metrics to quantify how well the two prints match and use these metrics to train a random forest that generates a probabilistic measurement of how likely two prints are to have originated from the same outsole. We assess the generalisability of machine learning methods trained on lab shoeprint scans to more realistic crime scene shoeprint data by evaluating the accuracy of our methods on several shoeprint scenarios: partial prints, prints with varying levels of blurriness, prints with different amounts of wear, and prints from different shoe models. We find that models trained on one type of shoeprint yield extremely high levels of accuracy when tested on shoeprint pairs of the same scenario but fail to generalise to other scenarios. We also discover that models trained on a variety of scenarios predict almost as accurately as models trained on specific scenarios.

This paper introduces a new tool, OccCANINE, to automatically transform occupational descriptions into the HISCO classification system. The manual work involved in processing and classifying occupational descriptions is error-prone, tedious, and time-consuming. We finetune a preexisting language model (CANINE) to do this automatically, thereby performing in seconds and minutes what previously took days and weeks. The model is trained on 14 million pairs of occupational descriptions and HISCO codes in 13 different languages contributed by 22 different sources. Our approach is shown to have accuracy, recall, and precision above 90 percent. Our tool breaks the metaphorical HISCO barrier and makes this data readily available for analysis of occupational structures with broad applicability in economics, economic history, and various related disciplines.