随着人工智能系统变得越来越强大和普遍，人们对机器的道德或缺乏道德的关注变得越来越关注。然而，向机器讲授道德是一项艰巨的任务，因为道德仍然是人类中最激烈的争论问题之一，更不用说AI了。但是，部署到数百万用户的现有AI系统已经在做出充满道德影响的决策，这构成了一个看似不可能的挑战：教学机器的道德意义，而人类继续努力努力。为了探索这一挑战，我们介绍了Delphi，这是一个基于深层神经网络的实验框架，直接训练了描述性道德判断，例如，“帮助朋友”通常是不错的，而“帮助朋友传播假新闻”不是。经验结果提供了对机器伦理的承诺和局限性的新见解。面对新的道德情况，德尔菲（Delphi）表现出强大的概括能力，而现成的神经网络模型表现出明显差的判断，包括不公正的偏见，证实了对明确教学机器的道德意义的必要性。然而，德尔菲并不完美，表现出对普遍性偏见和不一致的敏感性。尽管如此，我们还是展示了不完美的Delphi的积极用例，包括在其他不完美的AI系统中将其用作组件模型。重要的是，我们根据著名的道德理论来解释Delphi的运营化，这使我们提出了重要的未来研究问题。

This paper expounds the design and control of a new Variable Stiffness Series Elastic Actuator (VSSEA). It is established by employing a modular mechanical design approach that allows us to effectively optimise the stiffness modulation characteristics and power density of the actuator. The proposed VSSEA possesses the following features: i) no limitation in the work-range of output link, ii) a wide range of stiffness modulation (~20Nm/rad to ~1KNm/rad), iii) low-energy-cost stiffness modulation at equilibrium and non-equilibrium positions, iv) compact design and high torque density (~36Nm/kg), and v) high-speed stiffness modulation (~3000Nm/rad/s). Such features can help boost the safety and performance of many advanced robotic systems, e.g., a cobot that physically interacts with unstructured environments and an exoskeleton that provides physical assistance to human users. These features can also enable us to utilise variable stiffness property to attain various regulation and trajectory tracking control tasks only by employing conventional controllers, eliminating the need for synthesising complex motion control systems in compliant actuation. To this end, it is experimentally demonstrated that the proposed VSSEA is capable of precisely tracking desired position and force control references through the use of conventional Proportional-Integral-Derivative (PID) controllers.

Targeted syntactic evaluations of language models ask whether models show stable preferences for syntactically acceptable content over minimal-pair unacceptable inputs. Most targeted syntactic evaluation datasets ask models to make these judgements with just a single context-free sentence as input. This does not match language models' training regime, in which input sentences are always highly contextualized by the surrounding corpus. This mismatch raises an important question: how robust are models' syntactic judgements in different contexts? In this paper, we investigate the stability of language models' performance on targeted syntactic evaluations as we vary properties of the input context: the length of the context, the types of syntactic phenomena it contains, and whether or not there are violations of grammaticality. We find that model judgements are generally robust when placed in randomly sampled linguistic contexts. However, they are substantially unstable for contexts containing syntactic structures matching those in the critical test content. Among all tested models (GPT-2 and five variants of OPT), we significantly improve models' judgements by providing contexts with matching syntactic structures, and conversely significantly worsen them using unacceptable contexts with matching but violated syntactic structures. This effect is amplified by the length of the context, except for unrelated inputs. We show that these changes in model performance are not explainable by simple features matching the context and the test inputs, such as lexical overlap and dependency overlap. This sensitivity to highly specific syntactic features of the context can only be explained by the models' implicit in-context learning abilities.

Neural information retrieval (IR) systems have progressed rapidly in recent years, in large part due to the release of publicly available benchmarking tasks. Unfortunately, some dimensions of this progress are illusory: the majority of the popular IR benchmarks today focus exclusively on downstream task accuracy and thus conceal the costs incurred by systems that trade away efficiency for quality. Latency, hardware cost, and other efficiency considerations are paramount to the deployment of IR systems in user-facing settings. We propose that IR benchmarks structure their evaluation methodology to include not only metrics of accuracy, but also efficiency considerations such as a query latency and the corresponding cost budget for a reproducible hardware setting. For the popular IR benchmarks MS MARCO and XOR-TyDi, we show how the best choice of IR system varies according to how these efficiency considerations are chosen and weighed. We hope that future benchmarks will adopt these guidelines toward more holistic IR evaluation.

White matter bundle segmentation is a cornerstone of modern tractography to study the brain's structural connectivity in domains such as neurological disorders, neurosurgery, and aging. In this study, we present FIESTA (FIber gEneration and bundle Segmentation in Tractography using Autoencoders), a reliable and robust, fully automated, and easily semi-automatically calibrated pipeline based on deep autoencoders that can dissect and fully populate WM bundles. Our framework allows the transition from one anatomical bundle definition to another with marginal calibrating time. This pipeline is built upon FINTA, CINTA, and GESTA methods that demonstrated how autoencoders can be used successfully for streamline filtering, bundling, and streamline generation in tractography. Our proposed method improves bundling coverage by recovering hard-to-track bundles with generative sampling through the latent space seeding of the subject bundle and the atlas bundle. A latent space of streamlines is learned using autoencoder-based modeling combined with contrastive learning. Using an atlas of bundles in standard space (MNI), our proposed method segments new tractograms using the autoencoder latent distance between each tractogram streamline and its closest neighbor bundle in the atlas of bundles. Intra-subject bundle reliability is improved by recovering hard-to-track streamlines, using the autoencoder to generate new streamlines that increase each bundle's spatial coverage while remaining anatomically meaningful. Results show that our method is more reliable than state-of-the-art automated virtual dissection methods such as RecoBundles, RecoBundlesX, TractSeg, White Matter Analysis and XTRACT. Overall, these results show that our framework improves the practicality and usability of current state-of-the-art bundling framework

We present the CUNI-Bergamot submission for the WMT22 General translation task. We compete in English$\rightarrow$Czech direction. Our submission further explores block backtranslation techniques. Compared to the previous work, we measure performance in terms of COMET score and named entities translation accuracy. We evaluate performance of MBR decoding compared to traditional mixed backtranslation training and we show a possible synergy when using both of the techniques simultaneously. The results show that both approaches are effective means of improving translation quality and they yield even better results when combined.

An effective aggregation of node features into a graph-level representation via readout functions is an essential step in numerous learning tasks involving graph neural networks. Typically, readouts are simple and non-adaptive functions designed such that the resulting hypothesis space is permutation invariant. Prior work on deep sets indicates that such readouts might require complex node embeddings that can be difficult to learn via standard neighborhood aggregation schemes. Motivated by this, we investigate the potential of adaptive readouts given by neural networks that do not necessarily give rise to permutation invariant hypothesis spaces. We argue that in some problems such as binding affinity prediction where molecules are typically presented in a canonical form it might be possible to relax the constraints on permutation invariance of the hypothesis space and learn a more effective model of the affinity by employing an adaptive readout function. Our empirical results demonstrate the effectiveness of neural readouts on more than 40 datasets spanning different domains and graph characteristics. Moreover, we observe a consistent improvement over standard readouts (i.e., sum, max, and mean) relative to the number of neighborhood aggregation iterations and different convolutional operators.

Despite the rapid progress of open-domain generation-based conversational agents, most deployed systems treat dialogue contexts as single-turns, while systems dealing with multi-turn contexts are less studied. There is a lack of a reliable metric for evaluating multi-turn modelling, as well as an effective solution for improving it. In this paper, we focus on an essential component of multi-turn generation-based conversational agents: context attention distribution, i.e. how systems distribute their attention on dialogue's context. For evaluation of this component, We introduce a novel attention-mechanism-based metric: DAS ratio. To improve performance on this component, we propose an optimization strategy that employs self-contained distractions. Our experiments on the Ubuntu chatlogs dataset show that models with comparable perplexity can be distinguished by their ability on context attention distribution. Our proposed optimization strategy improves both non-hierarchical and hierarchical models on the proposed metric by about 10% from baselines.

负责任的AI被广泛认为是我们时代最大的科学挑战之一，也是释放AI市场并增加采用率的关键。为了应对负责任的AI挑战，最近已经发布了许多AI伦理原则框架，AI系统应该符合这些框架。但是，没有进一步的最佳实践指导，从业者除了真实性之外没有什么。同样，在算法级别而不是系统级的算法上进行了重大努力，主要集中于数学无关的道德原则（例如隐私和公平）的一部分。然而，道德问题在开发生命周期的任何步骤中都可能发生，从而超过AI算法和模型以外的系统的许多AI，非AI和数据组件。为了从系统的角度操作负责任的AI，在本文中，我们采用了一种面向模式的方法，并根据系统的多媒体文献综述（MLR）的结果提出了负责任的AI模式目录。与其呆在道德原则层面或算法层面上，我们专注于AI系统利益相关者可以在实践中采取的模式，以确保开发的AI系统在整个治理和工程生命周期中负责。负责的AI模式编目将模式分为三组：多层次治理模式，可信赖的过程模式和负责任的逐设计产品模式。这些模式为利益相关者实施负责任的AI提供了系统性和可行的指导。

我们在新定义的触发警告分配的计算任务上介绍了第一个数据集和评估结果。标记的语料库数据是根据我们自己的档案（AO3）（一个著名的幻想网站）托管的叙事作品编制的。在本文中，我们专注于最常见的触发类型（暴力），并定义文档级二进制分类任务，即是否将暴力触发警告分配给幻想小说，并利用AO3作者提供的警告标签。通过对Corpora进行了四个评估设置培训的SVM和BERT模型，我们编制的汇编$ f_1 $结果范围从0.585到0.798，证明暴力触发警告任务是可行的，这是一项不平凡的任务。