Open-textured terms in written rules are typically settled through interpretive argumentation. Ongoing work has attempted to catalogue the schemes used in such interpretive argumentation. But how can the use of these schemes affect the way in which people actually use and reason over the proper interpretations of open-textured terms? Using the interpretive argument-eliciting game Aporia as our framework, we carried out an empirical study to answer this question. Differing from previous work, we did not allow participants to argue for interpretations arbitrarily, but to only use arguments that fit with a given set of interpretive argument templates. Finally, we analyze the results captured by this new dataset, specifically focusing on practical implications for the development of interpretation-capable artificial reasoners.

There has been a recent resurgence in the area of explainable artificial intelligence as researchers and practitioners seek to make their algorithms more understandable. Much of this research is focused on explicitly explaining decisions or actions to a human observer, and it should not be controversial to say that looking at how humans explain to each other can serve as a useful starting point for explanation in artificial intelligence. However, it is fair to say that most work in explainable artificial intelligence uses only the researchers' intuition of what constitutes a 'good' explanation. There exists vast and valuable bodies of research in philosophy, psychology, and cognitive science of how people define, generate, select, evaluate, and present explanations, which argues that people employ certain cognitive biases and social expectations towards the explanation process. This paper argues that the field of explainable artificial intelligence should build on this existing research, and reviews relevant papers from philosophy, cognitive psychology/science, and social psychology, which study these topics. It draws out some important findings, and discusses ways that these can be infused with work on explainable artificial intelligence.

This volume contains revised versions of the papers selected for the third volume of the Online Handbook of Argumentation for AI (OHAAI). Previously, formal theories of argument and argument interaction have been proposed and studied, and this has led to the more recent study of computational models of argument. Argumentation, as a field within artificial intelligence (AI), is highly relevant for researchers interested in symbolic representations of knowledge and defeasible reasoning. The purpose of this handbook is to provide an open access and curated anthology for the argumentation research community. OHAAI is designed to serve as a research hub to keep track of the latest and upcoming PhD-driven research on the theory and application of argumentation in all areas related to AI.

我们介绍了Sparrow，这是一个寻求信息的对话代理，与提示的语言模型基线相比，训练有素，更有帮助，正确和无害。我们使用从人类反馈中的强化学习来培训我们的模型，以帮助人类评估者判断代理人的行为。首先，为了使我们的代理人更有帮助和无害，我们将良好对话的要求分解为代理人应遵循的自然语言规则，并分别向评估者询问每个规则。我们证明，这种崩溃使我们能够收集对代理行为的更多针对性的人类判断，并允许更有效的规则条件奖励模型。其次，我们的代理商在收集对模型声明的偏好判决时提供了支持事实主张的来源的证据。对于事实问题，麻雀提供的证据支持了78％的时间。比基线比基线更享受麻雀，同时对人类的对抗性探测更具弹性，在探测时只有8％的时间违反了我们的规则。最后，我们进行了广泛的分析，表明尽管我们的模型学会遵守我们的规则，但它可以表现出分布偏见。

We argue that the attempt to build morality into machines is subject to what we call the Interpretation problem, whereby any rule we give the machine is open to infinite interpretation in ways that we might morally disapprove of, and that the interpretation problem in Artificial Intelligence is an illustration of Wittgenstein's general claim that no rule can contain the criteria for its own application. Using games as an example, we attempt to define the structure of normative spaces and argue that any rule-following within a normative space is guided by values that are external to that space and which cannot themselves be represented as rules. In light of this problem, we analyse the types of mistakes an artificial moral agent could make and we make suggestions about how to build morality into machines by getting them to interpret the rules we give in accordance with these external values, through explicit moral reasoning and the presence of structured values, the adjustment of causal power assigned to the agent and interaction with human agents, such that the machine develops a virtuous character and the impact of the interpretation problem is minimised.

我们回顾了有关模型的文献，这些文献试图解释具有金钱回报的正常形式游戏所描述的社交互动中的人类行为。我们首先涵盖社会和道德偏好。然后，我们专注于日益增长的研究，表明人们对描述行动的语言做出反应，尤其是在激活道德问题时。最后，我们认为行为经济学正处于向基于语言的偏好转变的范式中，这将需要探索新的模型和实验设置。

\ EMPH {人工智能}（AI）系统越来越多地参与影响我们生活的决策，确保自动决策是公平的，道德已经成为最优先事项。直观地，我们觉得类似人的决定，人工代理人的判断应该必然地以一些道德原则为基础。然而，如果有关决定所基础的所有有关因素的全部信息，可以真正伦理（人类或人为）和公平（根据任何道德理论）和公平（根据公平的任何概念）的规定在决策时。这提出了两个问题：（1）在设置中，我们依赖使用通过监督学习获得的分类器的AI系统，存在一些感应/泛化，即使在学习期间也可能不存在一些相关属性。 （2）根据游戏揭示任何 - 无论是道德的纯策略都不可避免地易于剥削，建模这些决定。此外，在许多游戏中，只能通过使用混合策略来获得纳什均衡，即实现数学上最佳结果，决定必须随机化。在本文中，我们认为，在监督学习设置中，存在至少以及确定性分类器的随机分类器，因此在许多情况下可能是最佳选择。我们支持我们的理论效果，具有一个实证研究，表明对随机人工决策者的积极社会态度，并讨论了与使用与当前的AI政策和标准化举措相关的随机分类器相关的一些政策和实施问题。

随着近期自然语言生成（NLG）模型的各种应用程序的改进，它变得必须具有识别和评估NLG输出是否仅共享关于外部世界的可验证信息的手段。在这项工作中，我们提出了一个归属于识别的来源（AIS）的新评估框架，用于评估自然语言生成模型的输出，当这种输出涉及外部世界时。我们首先定义AIS，并引入两级注释管道，用于允许注释器根据AIS指南适当地评估模型输出。通过人为评估研究，我们在三个代数据集（会话QA域中的两个中和总结一下，概括地验证了这种方法，表明AIS可以作为测量模型生成的语句是否支持基础来源的常见框架。我们释放人类评估研究指南。

情绪分析中最突出的任务是为文本分配情绪，并了解情绪如何在语言中表现出来。自然语言处理的一个重要观察结果是，即使没有明确提及情感名称，也可以通过单独参考事件来隐式传达情绪。在心理学中，被称为评估理论的情感理论类别旨在解释事件与情感之间的联系。评估可以被形式化为变量，通过他们认为相关的事件的人们的认知评估来衡量认知评估。其中包括评估事件是否是新颖的，如果该人认为自己负责，是否与自己的目标以及许多其他人保持一致。这样的评估解释了哪些情绪是基于事件开发的，例如，新颖的情况会引起惊喜或不确定后果的人可能引起恐惧。我们在文本中分析了评估理论对情绪分析的适用性，目的是理解注释者是否可以可靠地重建评估概念，如果可以通过文本分类器预测，以及评估概念是否有助于识别情感类别。为了实现这一目标，我们通过要求人们发短信描述触发特定情绪并披露其评估的事件来编译语料库。然后，我们要求读者重建文本中的情感和评估。这种设置使我们能够衡量是否可以纯粹从文本中恢复情绪和评估，并为判断模型的绩效指标提供人体基准。我们将文本分类方法与人类注释者的比较表明，两者都可以可靠地检测出具有相似性能的情绪和评估。我们进一步表明，评估概念改善了文本中情绪的分类。

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。

As text generated by large language models proliferates, it becomes vital to understand how humans engage with such text, and whether or not they are able to detect when the text they are reading did not originate with a human writer. Prior work on human detection of generated text focuses on the case where an entire passage is either human-written or machine-generated. In this paper, we study a more realistic setting where text begins as human-written and transitions to being generated by state-of-the-art neural language models. We show that, while annotators often struggle at this task, there is substantial variance in annotator skill and that given proper incentives, annotators can improve at this task over time. Furthermore, we conduct a detailed comparison study and analyze how a variety of variables (model size, decoding strategy, fine-tuning, prompt genre, etc.) affect human detection performance. Finally, we collect error annotations from our participants and use them to show that certain textual genres influence models to make different types of errors and that certain sentence-level features correlate highly with annotator selection. We release the RoFT dataset: a collection of over 21,000 human annotations paired with error classifications to encourage future work in human detection and evaluation of generated text.

Advocates of algorithmic techniques like data mining argue that these techniques eliminate human biases from the decision-making process. But an algorithm is only as good as the data it works with. Data is frequently imperfect in ways that allow these algorithms to inherit the prejudices of prior decision makers. In other cases, data may simply reflect the widespread biases that persist in society at large. In still others, data mining can discover surprisingly useful regularities that are really just preexisting patterns of exclusion and inequality. Unthinking reliance on data mining can deny historically disadvantaged and vulnerable groups full participation in society. Worse still, because the resulting discrimination is almost always an unintentional emergent property of the algorithm's use rather than a conscious choice by its programmers, it can be unusually hard to identify the source of the problem or to explain it to a court. This Essay examines these concerns through the lens of American antidiscrimination law-more particularly, through Title

道德是人类最长的智力努力之一。近年来，AI和NLP的领域试图撰写与学习系统的与人类相互作用的学习系统，应该被限制为行为道德。该静脉中的一个提议是建立道德模型，可以采取任意文本，并输出关于所描述的情况的道德判断。在这项工作中，我们专注于对最近提出的Delphi模型的单一案例研究，并为该项目的建议自动化道德判决提供了批评。通过对Delphi的审计，我们检查更广泛的问题，适用于任何类似的尝试。我们讨论了机器道德如何通过专注于技术的当前和近期使用技术的方式来讨论机器伦理，以透明度，民主价值观，并允许直接的责任。

事实证明，在学习环境中，社会智能代理（SIA）的部署在不同的应用领域具有多个优势。社会代理创作工具使场景设计师能够创造出对SIAS行为的高度控制的量身定制体验，但是，另一方面，这是有代价的，因为该方案及其创作的复杂性可能变得霸道。在本文中，我们介绍了可解释的社会代理创作工具的概念，目的是分析社会代理的创作工具是否可以理解和解释。为此，我们检查了创作工具Fatima-Toolkit是否可以理解，并且从作者的角度来看，其创作步骤可以解释。我们进行了两项用户研究，以定量评估Fatima-Toolkit的解释性，可理解性和透明度，从场景设计师的角度来看。关键发现之一是，法蒂玛 - 库尔基特（Fatima-Toolkit）的概念模型通常是可以理解的，但是基于情感的概念并不那么容易理解和使用。尽管关于Fatima-Toolkit的解释性有一些积极的方面，但仍需要取得进展，以实现完全可以解释的社会代理商创作工具。我们提供一组关键概念和可能的解决方案，可以指导开发人员构建此类工具。

我们介绍了NLP社区Metasurvey的结果。从2022年5月到2022年6月，该调查引起了关于有争议的问题的意见，包括该领域的行业影响，对AGI和道德规范的关注。我们的结果将具体数字置于几个争议中：例如，受访者几乎完全将有关人工通用智能的重要性的问题分为一半，语言模型是否理解语言以及语言结构的必要性以及解决NLP问题的必要性。此外，调查提出了元问题，要求受访者预测调查响应的分布。这不仅使我们不仅可以深入了解NLP研究人员所拥有的各种信念，还可以揭示社区预测与现实不符的错误社会学信念。我们在各种问题上发现这种不匹配。除其他结果外，社区大大高估了其对基准的实用性的信念，以及扩展解决现实世界中问题的潜力，同时低估了其对语言结构，归纳偏见和跨学科科学重要性的信念。

The optimal liability framework for AI systems remains an unsolved problem across the globe. In a much-anticipated move, the European Commission advanced two proposals outlining the European approach to AI liability in September 2022: a novel AI Liability Directive and a revision of the Product Liability Directive. They constitute the final, and much-anticipated, cornerstone of AI regulation in the EU. Crucially, the liability proposals and the EU AI Act are inherently intertwined: the latter does not contain any individual rights of affected persons, and the former lack specific, substantive rules on AI development and deployment. Taken together, these acts may well trigger a Brussels effect in AI regulation, with significant consequences for the US and other countries. This paper makes three novel contributions. First, it examines in detail the Commission proposals and shows that, while making steps in the right direction, they ultimately represent a half-hearted approach: if enacted as foreseen, AI liability in the EU will primarily rest on disclosure of evidence mechanisms and a set of narrowly defined presumptions concerning fault, defectiveness and causality. Hence, second, the article suggests amendments, which are collected in an Annex at the end of the paper. Third, based on an analysis of the key risks AI poses, the final part of the paper maps out a road for the future of AI liability and regulation, in the EU and beyond. This includes: a comprehensive framework for AI liability; provisions to support innovation; an extension to non-discrimination/algorithmic fairness, as well as explainable AI; and sustainability. I propose to jump-start sustainable AI regulation via sustainability impact assessments in the AI Act and sustainable design defects in the liability regime. In this way, the law may help spur not only fair AI and XAI, but potentially also sustainable AI (SAI).

We are currently unable to specify human goals and societal values in a way that reliably directs AI behavior. Law-making and legal interpretation form a computational engine that converts opaque human values into legible directives. "Law Informs Code" is the research agenda capturing complex computational legal processes, and embedding them in AI. Similar to how parties to a legal contract cannot foresee every potential contingency of their future relationship, and legislators cannot predict all the circumstances under which their proposed bills will be applied, we cannot ex ante specify rules that provably direct good AI behavior. Legal theory and practice have developed arrays of tools to address these specification problems. For instance, legal standards allow humans to develop shared understandings and adapt them to novel situations. In contrast to more prosaic uses of the law (e.g., as a deterrent of bad behavior through the threat of sanction), leveraged as an expression of how humans communicate their goals, and what society values, Law Informs Code. We describe how data generated by legal processes (methods of law-making, statutory interpretation, contract drafting, applications of legal standards, legal reasoning, etc.) can facilitate the robust specification of inherently vague human goals. This increases human-AI alignment and the local usefulness of AI. Toward society-AI alignment, we present a framework for understanding law as the applied philosophy of multi-agent alignment. Although law is partly a reflection of historically contingent political power - and thus not a perfect aggregation of citizen preferences - if properly parsed, its distillation offers the most legitimate computational comprehension of societal values available. If law eventually informs powerful AI, engaging in the deliberative political process to improve law takes on even more meaning.

本文确定了数据驱动系统中的数据最小化和目的限制的两个核心数据保护原理。虽然当代数据处理实践似乎与这些原则的赔率达到差异，但我们证明系统可以在技术上使用的数据远远少于目前的数据。此观察是我们详细的技术法律分析的起点，揭示了妨碍了妨碍了实现的障碍，并举例说明了在实践中应用数据保护法的意外权衡。我们的分析旨在向辩论提供关于数据保护对欧盟人工智能发展的影响，为数据控制员，监管机构和研究人员提供实际行动点。

Alphazero，Leela Chess Zero和Stockfish Nnue革新了计算机国际象棋。本书对此类引擎的技术内部工作进行了完整的介绍。该书分为四个主要章节 - 不包括第1章（简介）和第6章（结论）：第2章引入神经网络，涵盖了所有用于构建深层网络的基本构建块，例如Alphazero使用的网络。内容包括感知器，后传播和梯度下降，分类，回归，多层感知器，矢量化技术，卷积网络，挤压网络，挤压和激发网络，完全连接的网络，批处理归一化和横向归一化和跨性线性单位，残留层，剩余层，过度效果和底漆。第3章介绍了用于国际象棋发动机以及Alphazero使用的经典搜索技术。内容包括minimax，alpha-beta搜索和蒙特卡洛树搜索。第4章展示了现代国际象棋发动机的设计。除了开创性的Alphago，Alphago Zero和Alphazero我们涵盖Leela Chess Zero，Fat Fritz，Fat Fritz 2以及有效更新的神经网络（NNUE）以及MAIA。第5章是关于实施微型α。 Shexapawn是国际象棋的简约版本，被用作为此的示例。 Minimax搜索可以解决六ap峰，并产生了监督学习的培训位置。然后，作为比较，实施了类似Alphazero的训练回路，其中通过自我游戏进行训练与强化学习结合在一起。最后，比较了类似α的培训和监督培训。

自论证挖掘领域成立以来，在法律话语中识别，分类和分析的论点一直是研究的重要领域。但是，自然语言处理（NLP）研究人员的模型模型与法院决策中的注释论点与法律专家理解和分析法律论证的方式之间存在重大差异。尽管计算方法通常将论点简化为通用的前提和主张，但法律研究中的论点通常表现出丰富的类型，对于获得一般法律的特定案例和应用很重要。我们解决了这个问题，并做出了一些实质性的贡献，以推动该领域的前进。首先，我们在欧洲人权法院（ECHR）诉讼中为法律论点设计了新的注释计划，该计划深深植根于法律论证研究的理论和实践中。其次，我们编译和注释了373项法院判决（230万令牌和15K注释的论点跨度）的大量语料库。最后，我们训练一个论证挖掘模型，该模型胜过法律NLP领域中最先进的模型，并提供了彻底的基于专家的评估。所有数据集和源代码均可在https://github.com/trusthlt/mining-legal-arguments的开放lincenses下获得。