Two-and-a-half years ago, technology wizard and Stanford University Master of Science in Computer Science graduate David Gunningjoined with DARPA, the Defense Advanced Research Projects Agency, to manage a program to develop explainable artificial intelligence. And listen up: The XAI arena, as it's abbreviated, is where we want to head -- this is where technology development ought to focus. XAI is the common-sense older brother in a digitized world filled with flashy, privacy-invading, data-gobbling gadgets and machine-controlling bullies. The goal of XAI, Gunning said, in a recent telephone conversation, is not so much to "take human thinking and put it into machines," as nearly all of today's artificial intelligence seeks to do. Rather, XAI's aim is to equip the machine with the ability to tell its human operators why it arrives at the conclusions it does -- to make the machine explain itself, so to speak. That means humans still stay at the helm.

Are we really committed to prohibiting chemical weapons, or only committed if no one is upset, only committed if no one complains, only committed if no one is put out?

BRUSSELS – Member nations of the global chemical weapons watchdog voted Wednesday to give the organization the authority to apportion blame for illegal attacks, expanding its powers following a bitter dispute pitting Britain and its Western allies against Russia and Syria. An 82-24 vote provided the two-thirds majority needed to enlarge the purview of the Organization for the Prohibition of Chemical Weapons. The organization was created to implement a 1997 treaty that banned chemical weapons, but lacked a mandate to name the parties it found responsible for using them. Many participating nations saw the inability to assign responsibility as a senseless hamstring, especially after fatal chemical attacks during the war in Syria. Russia opposed adding a new license to the agency's portfolio, saying that was a decision that belonged to the United Nations.

From 2015 to 2017 a joint United Nations-OPCW team had been appointed to assign blame for chemical attacks in Syria. It found that Syrian government troops used nerve agent sarin and chorine barrel bombs on several occasions, while Islamic State militants were found to have used sulfur mustard.

Britain made its proposal in the wake of the chemical attacks on an ex-spy and his daughter in the English city of Salisbury, as well as in Syria's civil war and attacks by the Islamic State group in Iraq. Britain has accused Russia of using a nerve agent in the attempted assassination in March of former spy Sergei Skripal, which Moscow strongly denies.

Model reconciliation has been proposed as a way for an agent to explain its decisions to a human who may have a different understanding of the same planning problem by explaining its decisions in terms of these model differences.However, often the human's mental model (and hence the difference) is not known precisely and such explanations cannot be readily computed.In this paper, we show how the explanation generation process evolves in the presence of such model uncertainty or incompleteness by generating {\em conformant explanations} that are applicable to a set of possible models.We also show how such explanations can contain superfluous informationand how such redundancies can be reduced using conditional explanations to iterate with the human to attain common ground. Finally, we will introduce an anytime version of this approach and empirically demonstrate the trade-offs involved in the different forms of explanations in terms of the computational overhead for the agent and the communication overhead for the human.We illustrate these concepts in three well-known planning domains as well as in a demonstration on a robot involved in a typical search and reconnaissance scenario with an external human supervisor.

Abstract Dialectical Frameworks (ADFs) generalize Dung's argumentation frameworks allowing various relationships among arguments to be expressed in a systematic way. We further generalize ADFs so as to accommodate arbitrary acceptance degrees for the arguments. This makes ADFs applicable in domains where both the initial status of arguments and their relationship are only insufficiently specified by Boolean functions. We define all standard ADF semantics for the weighted case, including grounded, preferred and stable semantics. We illustrate our approach using acceptance degrees from the unit interval and show how other valuation structures can be integrated. In each case it is sufficient to specify how the generalized acceptance conditions are represented by formulas, and to specify the information ordering underlying the characteristic ADF operator. We also present complexity results for problems related to weighted ADFs.

To generate trust with their users, Explainable Artificial Intelligence (XAI) systems need to include an explanation model that can communicate the internal decisions, behaviours and actions to the interacting humans. Successful explanation involves both cognitive and social processes. In this paper we focus on the challenge of meaningful interaction between an explainer and an explainee and investigate the structural aspects of an explanation in order to propose a human explanation dialog model. We follow a bottom-up approach to derive the model by analysing transcripts of 398 different explanation dialog types. We use grounded theory to code and identify key components of which an explanation dialog consists. We carry out further analysis to identify the relationships between components and sequences and cycles that occur in a dialog. We present a generalized state model obtained by the analysis and compare it with an existing conceptual dialog model of explanation.

In particular, we clarify and make explicit all of the proofs mentioned therein, and provide many more examples to the definitions, in a way that should be helpful to readers approaching abstract argumentation theory for the first time. However, we provide minimal commentary and will refer the reader to Dung's paper for the intuitions behind various concepts. The appropriate mathematical prerequisites are provided in the appendices.

The first consideration when discussing transparency in AI should be data, the fuel that powers the algorithms. Companies should disclose where and how they got the data they used to fuel their AI systems' decisions. Consumers should own their data and should be privy to the myriad ways that businesses use and sell such information, which is often done without clear and conscious consumer consent. Because data is the foundation for all AI, it is valid to want to know where the data comes from and how it might explain biases and counterintuitive decisions that AI systems make. On the algorithmic side, grandstanding by IBM and other tech giants around the idea of "explainable AI" is nothing but virtue signaling that has no basis in reality.