One of the challenges of developing a summarization model arises from the difficulty in measuring the factual inconsistency of the generated text. In this study, we reinterpret the decoder overconfidence-regularizing objective suggested in (Miao et al., 2021) as a hallucination risk measurement to better estimate the quality of generated summaries. We propose a reference-free metric, HaRiM+, which only requires an off-the-shelf summarization model to compute the hallucination risk based on token likelihoods. Deploying it requires no additional training of models or ad-hoc modules, which usually need alignment to human judgments. For summary-quality estimation, HaRiM+ records state-of-the-art correlation to human judgment on three summary-quality annotation sets: FRANK, QAGS, and SummEval. We hope that our work, which merits the use of summarization models, facilitates the progress of both automated evaluation and generation of summary.

The final search query for the Systematic Literature Review (SLR) was conducted on 15th July 2022. Initially, we extracted 1707 journal and conference articles from the Scopus and Web of Science databases. Inclusion and exclusion criteria were then applied, and 58 articles were selected for the SLR. The findings show four dimensions that shape the AI explanation, which are format (explanation representation format), completeness (explanation should contain all required information, including the supplementary information), accuracy (information regarding the accuracy of the explanation), and currency (explanation should contain recent information). Moreover, along with the automatic representation of the explanation, the users can request additional information if needed. We have also found five dimensions of XAI effects: trust, transparency, understandability, usability, and fairness. In addition, we investigated current knowledge from selected articles to problematize future research agendas as research questions along with possible research paths. Consequently, a comprehensive framework of XAI and its possible effects on user behavior has been developed.

The rapid progress of machine learning interatomic potentials over the past couple of years produced a number of new architectures. Particularly notable among these are the Atomic Cluster Expansion (ACE), which unified many of the earlier ideas around atom density-based descriptors, and Neural Equivariant Interatomic Potentials (NequIP), a message passing neural network with equivariant features that showed state of the art accuracy. In this work, we construct a mathematical framework that unifies these models: ACE is generalised so that it can be recast as one layer of a multi-layer architecture. From another point of view, the linearised version of NequIP is understood as a particular sparsification of a much larger polynomial model. Our framework also provides a practical tool for systematically probing different choices in the unified design space. We demonstrate this by an ablation study of NequIP via a set of experiments looking at in- and out-of-domain accuracy and smooth extrapolation very far from the training data, and shed some light on which design choices are critical for achieving high accuracy. Finally, we present BOTNet (Body-Ordered-Tensor-Network), a much-simplified version of NequIP, which has an interpretable architecture and maintains accuracy on benchmark datasets.

Increasing traffic demands, higher levels of automation, and communication enhancements provide novel design opportunities for future air traffic controllers (ATCs). This article presents a novel deep reinforcement learning (DRL) controller to aid conflict resolution for autonomous free flight. Although DRL has achieved important advancements in this field, the existing works pay little attention to the explainability and safety issues related to DRL controllers, particularly the safety under adversarial attacks. To address those two issues, we design a fully explainable DRL framework wherein we: 1) decompose the coupled Q value learning model into a safety-awareness and efficiency (reach the target) one; and 2) use information from surrounding intruders as inputs, eliminating the needs of central controllers. In our simulated experiments, we show that by decoupling the safety-awareness and efficiency, we can exceed performance on free flight control tasks while dramatically improving explainability on practical. In addition, the safety Q learning module provides rich information about the safety situation of environments. To study the safety under adversarial attacks, we additionally propose an adversarial attack strategy that can impose both safety-oriented and efficiency-oriented attacks. The adversarial aims to minimize safety/efficiency by only attacking the agent at a few time steps. In the experiments, our attack strategy increases as many collisions as the uniform attack (i.e., attacking at every time step) by only attacking the agent four times less often, which provide insights into the capabilities and restrictions of the DRL in future ATC designs. The source code is publicly available at https://github.com/WLeiiiii/Gym-ATC-Attack-Project.

A parametric adaptive greedy Latent Space Dynamics Identification (gLaSDI) framework is developed for accurate, efficient, and certified data-driven physics-informed greedy auto-encoder simulators of high-dimensional nonlinear dynamical systems. In the proposed framework, an auto-encoder and dynamics identification models are trained interactively to discover intrinsic and simple latent-space dynamics. To effectively explore the parameter space for optimal model performance, an adaptive greedy sampling algorithm integrated with a physics-informed error indicator is introduced to search for optimal training samples on the fly, outperforming the conventional predefined uniform sampling. Further, an efficient k-nearest neighbor convex interpolation scheme is employed to exploit local latent-space dynamics for improved predictability. Numerical results demonstrate that the proposed method achieves 121 to 2,658x speed-up with 1 to 5% relative errors for radial advection and 2D Burgers dynamical problems.

Competition commissioner Margrethe Vestager aims to create a'transatlantic space for trustworthy AI', giving companies a single set of rules to follow. Brussels and Washington can create a common space for trustworthy AI so that companies can comply with both EU and US artificial intelligence guidelines by applying a single set of rules, the EU's competition commissioner has said. Margrethe Vestager's remarks, made in advance of the third EU-US Trade and Technology Council (TTC) meeting, which will take place on December 5, go further than ever before in aiming to align rules over the technology. Speaking in Brussels on 21 November, she said that progress made by the EU and US should "pave the way for a transatlantic sort of space for trustworthy AI." If the US and EU can agree on a common rulebook for AI it would become the de facto global standard, given the weight of the two economies.

Researchers at MIT's Center for Bits and Atoms are working on an ambitious project, designing robots that effectively self-assemble. The team admits that the goal of an autonomous self-building robot is still "years away," but the work has thus far demonstrated positive results. At the system's center are voxels (a term borrowed from computer graphics), which carry power and data that can be shared between pieces. The pieces form the foundation of the robot, grabbing and attaching additional voxels before moving across the grid for further assembly. The researchers note in an associated paper published in Nature, "Our approach challenges the convention that larger constructions need larger machines to build them, and could be applied in areas that today either require substantial capital investments for fixed infrastructure or are altogether unfeasible."

Okay, let's talk about killer robots. It's a concept that long ago leapt from the pages of science fiction to reality, depending on how loose a definition you use for "robot." Military drones abandoned Asimov's First Law of Robotics -- "A robot may not injure a human being or, through inaction, allow a human being to come to harm" -- decades ago. The topic has been simmering again of late due to the increasing prospect of killer robots in domestic law enforcement. One of the era's best known robot makers, Boston Dynamics, raised some public policy red flags when it showcased footage of its Spot robot being deployed as part of Massachusetts State Police training exercises on our stage back in 2019.

This is not the first time that "World of Warcraft" has encountered hurdles in China. The9, Blizzard's distributor for "World of Warcraft" in China at the time, suffered a disastrous drop in revenue as a result. That same year, Blizzard began its partnership with NetEase.

Risk prediction has permeated many aspects of modern life, including health care. Algorithms developed using advanced statistical methods have been used to identify hospitalized adults at risk of clinical deterioration, reduce hospital readmission rates, and improve resource allocation and health care use. These methods have also been used to develop predictive models for overdose risk among specific patient populations. Most of these overdose-specific applications, however, have been limited to health care settings using health care utilization or insurance claims data. State and local governments are increasingly integrating health- and non-health-sector data for public health purposes, creating an opportunity to use these data to improve overdose risk prediction models.