A Digital Twin (DT) is a simulation of a physical system that provides information to make decisions that add economic, social or commercial value. The behaviour of a physical system changes over time, a DT must therefore be continually updated with data from the physical systems to reflect its changing behaviour. For resource-constrained systems, updating a DT is non-trivial because of challenges such as on-board learning and the off-board data transfer. This paper presents a framework for updating data-driven DTs of resource-constrained systems geared towards system health monitoring. The proposed solution consists of: (1) an on-board system running a light-weight DT allowing the prioritisation and parsimonious transfer of data generated by the physical system; and (2) off-board robust updating of the DT and detection of anomalous behaviours. Two case studies are considered using a production gas turbine engine system to demonstrate the digital representation accuracy for real-world, time-varying physical systems.

As language models (LMs) scale, they develop many novel behaviors, good and bad, exacerbating the need to evaluate how they behave. Prior work creates evaluations with crowdwork (which is time-consuming and expensive) or existing data sources (which are not always available). Here, we automatically generate evaluations with LMs. We explore approaches with varying amounts of human effort, from instructing LMs to write yes/no questions to making complex Winogender schemas with multiple stages of LM-based generation and filtering. Crowdworkers rate the examples as highly relevant and agree with 90-100% of labels, sometimes more so than corresponding human-written datasets. We generate 154 datasets and discover new cases of inverse scaling where LMs get worse with size. Larger LMs repeat back a dialog user's preferred answer ("sycophancy") and express greater desire to pursue concerning goals like resource acquisition and goal preservation. We also find some of the first examples of inverse scaling in RL from Human Feedback (RLHF), where more RLHF makes LMs worse. For example, RLHF makes LMs express stronger political views (on gun rights and immigration) and a greater desire to avoid shut down. Overall, LM-written evaluations are high-quality and let us quickly discover many novel LM behaviors.

“感应头”是注意力头，它实现了一种简单的算法来完成令牌序列，例如[a] [b] ... [a] - > [b]。在这项工作中，我们提供了一个假设的初步和间接证据，即诱导头可能构成大型大型变压器模型中所有“文本学习”中大多数的机制（即减少在增加代币指数时损失的损失）。我们发现，诱导头在与秘密学习能力突然急剧上的急剧上升的位置完全相同，这是训练损失的颠簸。我们提出了六种互补的证据，认为诱导头可能是任何大小的变压器模型中一般性内部学习的机理来源。对于仅关注的小型模型，我们提供了有力的因果证据。对于具有MLP的较大模型，我们提供相关证据。

随着深度学习在关键任务系统中的越来越多的应用，越来越需要对神经网络的行为进行正式保证。确实，最近提出了许多用于验证神经网络的方法，但是这些方法通常以有限的可伸缩性或不足的精度而挣扎。许多最先进的验证方案中的关键组成部分是在网络中可以为特定输入域获得的神经元获得的值计算下限和上限 - 并且这些界限更紧密，验证的可能性越大，验证的可能性就越大。成功。计算这些边界的许多常见算法是符号结合传播方法的变化。其中，利用一种称为后替代的过程的方法特别成功。在本文中，我们提出了一种使背部替代产生更严格的界限的方法。为了实现这一目标，我们制定并最大程度地减少背部固定过程中发生的不精确错误。我们的技术是一般的，从某种意义上说，它可以将其集成到许多现有的符号结合的传播技术中，并且只有较小的修改。我们将方法作为概念验证工具实施，并且与执行背部替代的最先进的验证者相比，取得了有利的结果。

我们研究语言模型是否可以评估自己主张的有效性，并预测他们能够正确回答的问题。我们首先表明，当以正确的格式提供时，较大的模型在多样化的多项选择和True/False问题上进行了很好的校准。因此，我们可以通过要求模型首先提出答案，然后评估其答案正确的概率“ p（true）”来对开放式采样任务进行自我评估。我们发现在各种任务中，P（true）的表现，校准和缩放令人鼓舞。当我们允许模型考虑自己的许多样本之前，在预测一种特定可能性的有效性之前，自我评估的性能进一步改善。接下来，我们研究是否可以培训模型来预测“ P（ik）”，即“我知道”问题的概率，而无需参考任何特定提出的答案。模型在预测P（IK）方面表现良好，并且在跨任务中部分概括，尽管它们在新任务上的P（IK）校准方面遇到了困难。预测的p（IK）概率在存在相关的原始材料的情况下以及对数学单词问题解决方案的提示也适当增加。我们希望这些观察结果为培训更诚实的模型提供了基础，并研究了诚实对模型模仿人类写作以外的其他目标培训的案例的普遍性。

我们通过与与前面令牌的局部相似度，通过调节从大语料库检索的文档块来增强自动回归语言模型。尽管使用25美元\时分，我们的检索增强型变压器（RetroCro）的检索增强型变压器（RetroCr）对GPT-3和侏罗纪-1获得了可比性的性能。微调后，复古表演转换为下游知识密集型任务，如问题应答。复古结合了冷冻BERT猎犬，一种可微分的编码器和块状的横向机制，以预测基于数量级的令牌，而不是训练期间通常消耗的数量。我们通常从头开始训练复古，还可以快速改造预先接受的变压器，通过检索，仍然达到良好的性能。我们的工作通过以前所未有的规模开辟了通过显式内存改进语言模型的新途径。

燃气轮机发动机是复杂的机器，通常产生大量数据，并且需要仔细监控，以允许具有成本效益的预防性维护。在航空航天应用中，将所有测量数据返回到地面是昂贵的，通常会导致有用，高值，要丢弃的数据。因此，在实时检测，优先级和返回有用数据的能力是至关重要的。本文提出了由卷积神经网络常态模型描述的系统输出测量，实时优先考虑预防性维护决策者。由于燃气轮机发动机时变行为的复杂性，导出精确的物理模型难以困难，并且通常导致预测精度低的模型和与实时执行不相容。数据驱动的建模是一种理想的替代方案，生产高精度，资产特定模型，而无需从第一原理推导。我们提出了一种用于在线检测和异常数据的优先级的数据驱动系统。通过集成到深神经预测模型中的不确定管理，避免了偏离新的操作条件的数据评估。测试是对实际和合成数据进行的，显示对真实和合成故障的敏感性。该系统能够在低功耗嵌入式硬件上实时运行，目前正在部署Rolls-Royce Pearl 15发动机飞行试验。

鉴于大型语言模型的广泛能力，应该有可能朝着一般的文本的助手工作，这些助手与人类价值一致，这意味着它是有帮助，诚实的和无害的。在此方向上的初始遗传，我们研究简单的基线技术和评估，例如提示。我们发现，从模型规模增加适度的干预措施的好处，概括为各种对准评估，并不会损害大型模型的性能。接下来，我们调查与对齐，比较仿制，二进制歧视和排名偏好建模相关的几个培训目标的缩放趋势。我们发现排名优先级模型比模仿学习更好地表现得多，并且通常以模型大小更有利地缩放。相比之下，二进制歧视通常与模仿学习非常类似地执行和缩放。最后，我们研究了一种“偏好模型预训练阶段的培训阶段，其目的是在对人偏好的芬明时提高样本效率。

Learning to predict masked tokens in a sequence has been shown to be a powerful pretraining objective for large-scale language models. After training, such masked language models can provide distributions of tokens conditioned on bidirectional context. In this short draft, we show that such bidirectional conditionals often demonstrate considerable inconsistencies, i.e., they can not be derived from a coherent joint distribution when considered together. We empirically quantify such inconsistencies in the simple scenario of bigrams for two common styles of masked language models: T5-style and BERT-style. For example, we show that T5 models often confuse its own preference regarding two similar bigrams. Such inconsistencies may represent a theoretical pitfall for the research work on sampling sequences based on the bidirectional conditionals learned by BERT-style MLMs. This phenomenon also means that T5-style MLMs capable of infilling will generate discrepant results depending on how much masking is given, which may represent a particular trust issue.

We study the problem of planning under model uncertainty in an online meta-reinforcement learning (RL) setting where an agent is presented with a sequence of related tasks with limited interactions per task. The agent can use its experience in each task and across tasks to estimate both the transition model and the distribution over tasks. We propose an algorithm to meta-learn the underlying structure across tasks, utilize it to plan in each task, and upper-bound the regret of the planning loss. Our bound suggests that the average regret over tasks decreases as the number of tasks increases and as the tasks are more similar. In the classical single-task setting, it is known that the planning horizon should depend on the estimated model's accuracy, that is, on the number of samples within task. We generalize this finding to meta-RL and study this dependence of planning horizons on the number of tasks. Based on our theoretical findings, we derive heuristics for selecting slowly increasing discount factors, and we validate its significance empirically.