Explainable AI (XAI) is widely viewed as a sine qua non for ever-expanding AI research. A better understanding of the needs of XAI users, as well as human-centered evaluations of explainable models are both a necessity and a challenge. In this paper, we explore how HCI and AI researchers conduct user studies in XAI applications based on a systematic literature review. After identifying and thoroughly analyzing 85 core papers with human-based XAI evaluations over the past five years, we categorize them along the measured characteristics of explanatory methods, namely trust, understanding, fairness, usability, and human-AI team performance. Our research shows that XAI is spreading more rapidly in certain application domains, such as recommender systems than in others, but that user evaluations are still rather sparse and incorporate hardly any insights from cognitive or social sciences. Based on a comprehensive discussion of best practices, i.e., common models, design choices, and measures in user studies, we propose practical guidelines on designing and conducting user studies for XAI researchers and practitioners. Lastly, this survey also highlights several open research directions, particularly linking psychological science and human-centered XAI.

Retrieval-augmented in-context learning has emerged as a powerful approach for addressing knowledge-intensive tasks using frozen language models (LM) and retrieval models (RM). Existing work has combined these in simple "retrieve-then-read" pipelines in which the RM retrieves passages that are inserted into the LM prompt. To begin to fully realize the potential of frozen LMs and RMs, we propose Demonstrate-Search-Predict (DSP), a framework that relies on passing natural language texts in sophisticated pipelines between an LM and an RM. DSP can express high-level programs that bootstrap pipeline-aware demonstrations, search for relevant passages, and generate grounded predictions, systematically breaking down problems into small transformations that the LM and RM can handle more reliably. We have written novel DSP programs for answering questions in open-domain, multi-hop, and conversational settings, establishing in early evaluations new state-of-the-art in-context learning results and delivering 37-200%, 8-40%, and 80-290% relative gains against vanilla LMs, a standard retrieve-then-read pipeline, and a contemporaneous self-ask pipeline, respectively.

Semi-supervised learning (SSL) has made significant strides in the field of remote sensing. Finding a large number of labeled datasets for SSL methods is uncommon, and manually labeling datasets is expensive and time-consuming. Furthermore, accurately identifying remote sensing satellite images is more complicated than it is for conventional images. Class-imbalanced datasets are another prevalent phenomenon, and models trained on these become biased towards the majority classes. This becomes a critical issue with an SSL model's subpar performance. We aim to address the issue of labeling unlabeled data and also solve the model bias problem due to imbalanced datasets while achieving better accuracy. To accomplish this, we create "artificial" labels and train a model to have reasonable accuracy. We iteratively redistribute the classes through resampling using a distribution alignment technique. We use a variety of class imbalanced satellite image datasets: EuroSAT, UCM, and WHU-RS19. On UCM balanced dataset, our method outperforms previous methods MSMatch and FixMatch by 1.21% and 0.6%, respectively. For imbalanced EuroSAT, our method outperforms MSMatch and FixMatch by 1.08% and 1%, respectively. Our approach significantly lessens the requirement for labeled data, consistently outperforms alternative approaches, and resolves the issue of model bias caused by class imbalance in datasets.

Many real-world applications of language models (LMs), such as code autocomplete and writing assistance, involve human-LM interaction, but the main LM benchmarks are non-interactive, where a system produces output without human intervention. To evaluate human-LM interaction, we develop a framework, Human-AI Language-based Interaction Evaluation (H-LINE), that expands non-interactive evaluation along three dimensions, capturing (i) the interactive process, not only the final output; (ii) the first-person subjective experience, not just a third-party assessment; and (iii) notions of preference beyond quality. We then design five tasks ranging from goal-oriented to open-ended to capture different forms of interaction. On four state-of-the-art LMs (three variants of OpenAI's GPT-3 and AI21's J1-Jumbo), we find that non-interactive performance does not always result in better human-LM interaction and that first-person and third-party metrics can diverge, suggesting the importance of examining the nuances of human-LM interaction.

Identifying the production dates of historical manuscripts is one of the main goals for paleographers when studying ancient documents. Automatized methods can provide paleographers with objective tools to estimate dates more accurately. Previously, statistical features have been used to date digitized historical manuscripts based on the hypothesis that handwriting styles change over periods. However, the sparse availability of such documents poses a challenge in obtaining robust systems. Hence, the research of this article explores the influence of data augmentation on the dating of historical manuscripts. Linear Support Vector Machines were trained with k-fold cross-validation on textural and grapheme-based features extracted from historical manuscripts of different collections, including the Medieval Paleographical Scale, early Aramaic manuscripts, and the Dead Sea Scrolls. Results show that training models with augmented data improve the performance of historical manuscripts dating by 1% - 3% in cumulative scores. Additionally, this indicates further enhancement possibilities by considering models specific to the features and the documents' scripts.

Vehicle trajectory data has received increasing research attention over the past decades. With the technological sensing improvements such as high-resolution video cameras, in-vehicle radars and lidars, abundant individual and contextual traffic data is now available. However, though the data quantity is massive, it is by itself of limited utility for traffic research because of noise and systematic sensing errors, thus necessitates proper processing to ensure data quality. We draw particular attention to extracting high-resolution vehicle trajectory data from video cameras as traffic monitoring cameras are becoming increasingly ubiquitous. We explore methods for automatic trajectory data reconciliation, given "raw" vehicle detection and tracking information from automatic video processing algorithms. We propose a pipeline including a) an online data association algorithm to match fragments that are associated to the same object (vehicle), which is formulated as a min-cost network flow problem of a graph, and b) a trajectory reconciliation method formulated as a quadratic program to enhance raw detection data. The pipeline leverages vehicle dynamics and physical constraints to associate tracked objects when they become fragmented, remove measurement noise on trajectories and impute missing data due to fragmentations. The accuracy is benchmarked on a sample of manually-labeled data, which shows that the reconciled trajectories improve the accuracy on all the tested input data for a wide range of measures. An online version of the reconciliation pipeline is implemented and will be applied in a continuous video processing system running on a camera network covering a 4-mile stretch of Interstate-24 near Nashville, Tennessee.

We introduce a linguistically enhanced combination of pre-training methods for transformers. The pre-training objectives include POS-tagging, synset prediction based on semantic knowledge graphs, and parent prediction based on dependency parse trees. Our approach achieves competitive results on the Natural Language Inference task, compared to the state of the art. Specifically for smaller models, the method results in a significant performance boost, emphasizing the fact that intelligent pre-training can make up for fewer parameters and help building more efficient models. Combining POS-tagging and synset prediction yields the overall best results.

Modern statistical learning algorithms are capable of amazing flexibility, but struggle with interpretability. One possible solution is sparsity: making inference such that many of the parameters are estimated as being identically 0, which may be imposed through the use of nonsmooth penalties such as the $\ell_1$ penalty. However, the $\ell_1$ penalty introduces significant bias when high sparsity is desired. In this article, we retain the $\ell_1$ penalty, but define learnable penalty weights $\lambda_p$ endowed with hyperpriors. We start the article by investigating the optimization problem this poses, developing a proximal operator associated with the $\ell_1$ norm. We then study the theoretical properties of this variable-coefficient $\ell_1$ penalty in the context of penalized likelihood. Next, we investigate application of this penalty to Variational Bayes, developing a model we call the Sparse Bayesian Lasso which allows for behavior qualitatively like Lasso regression to be applied to arbitrary variational models. In simulation studies, this gives us the Uncertainty Quantification and low bias properties of simulation-based approaches with an order of magnitude less computation. Finally, we apply our methodology to a Bayesian lagged spatiotemporal regression model of internal displacement that occurred during the Iraqi Civil War of 2013-2017.

Single-cell reference atlases are large-scale, cell-level maps that capture cellular heterogeneity within an organ using single cell genomics. Given their size and cellular diversity, these atlases serve as high-quality training data for the transfer of cell type labels to new datasets. Such label transfer, however, must be robust to domain shifts in gene expression due to measurement technique, lab specifics and more general batch effects. This requires methods that provide uncertainty estimates on the cell type predictions to ensure correct interpretation. Here, for the first time, we introduce uncertainty quantification methods for cell type classification on single-cell reference atlases. We benchmark four model classes and show that currently used models lack calibration, robustness, and actionable uncertainty scores. Furthermore, we demonstrate how models that quantify uncertainty are better suited to detect unseen cell types in the setting of atlas-level cell type transfer.

Current technological advances open up new opportunities for bringing human-machine interaction to a new level of human-centered cooperation. In this context, a key issue is the semantic understanding of the environment in order to enable mobile robots more complex interactions and a facilitated communication with humans. Prerequisites are the vision-based registration of semantic objects and humans, where the latter are further analyzed for potential interaction partners. Despite significant research achievements, the reliable and fast registration of semantic information still remains a challenging task for mobile robots in real-world scenarios. In this paper, we present a vision-based system for mobile assistive robots to enable a semantic-aware environment perception without additional a-priori knowledge. We deploy our system on a mobile humanoid robot that enables us to test our methods in real-world applications.