The overall team performance will obviously get much better as we click on at least two of those cylinders. When we get some of our guys back in the next week, we're confident our offense is going to perform better. It's incumbent upon us, with our bullpen, to get back to what we were doing last year. We're confident we have the guys down there to perform way better than we have.

There is an increasing demand for algorithms to explain their outcomes. So far, there is no method that explains the rankings produced by a ranking algorithm. To address this gap we propose LISTEN, a LISTwise ExplaiNer, to explain rankings produced by a ranking algorithm. To efficiently use LISTEN in production, we train a neural network to learn the underlying explanation space created by LISTEN; we call this model Q-LISTEN. We show that LISTEN produces faithful explanations and that Q-LISTEN is able to learn these explanations. Moreover, we show that LISTEN is safe to use in a real world environment: users of a news recommendation system do not behave significantly differently when they are exposed to explanations generated by LISTEN instead of manually generated explanations.

The notion that we should understand how artificial intelligences make decisions is gaining increasing currency. As we face a future in which important decisions affecting the course of our lives may be made by artificial intelligence (AI), the idea that we should understand how AIs make decisions is gaining increasing currency. Which hill to position a 20-year-old soldier on, who gets (or does not get) a home mortgage, which treatment a cancer patient receives … such decisions, and many more, already are being made based on an often unverifiable technology. "The problem is that not all AI approaches are created equal," says Jeff Nicholson, a vice president at Pega Systems Inc., makers of AI-based Customer Relationship Management (CRM) software. "Certain'black box' approaches to AI are opaque and simply cannot be explained."

This paper builds on the recent ASPIC+ formalism, to develop a general framework for argumentation with preferences. We motivate a revised definition of conflict free sets of arguments, adapt ASPIC+ to accommodate a broader range of instantiating logics, and show that under some assumptions, the resulting framework satisfies key properties and rationality postulates. We then show that the generalised framework accommodates Tarskian logic instantiations extended with preferences, and then study instantiations of the framework by classical logic approaches to argumentation. We conclude by arguing that ASPIC+'s modelling of defeasible inference rules further testifies to the generality of the framework, and then examine and counter recent critiques of Dung's framework and its extensions to accommodate preferences.

CONSULT is a decision-support framework designed to help patients self-manage chronic conditions and adhere to agreed-upon treatment plans, in collaboration with healthcare professionals. The approach taken employs computational argumentation, a logic-based methodology that provides a formal means for reasoning with evidence by substantiating claims for and against particular conclusions. This paper outlines the architecture of CONSULT, illustrating how facts are gathered about the patient and various preferences of the patient and the clinician(s) involved. A logic-based representation of official treatment guidelines by various public health agencies is presented. Logical arguments are constructed from these facts and guidelines; these arguments are analysed to resolve inconsistencies concerning various treatment options and patient/clinician preferences. The claims of the justified arguments are the decisions recommended by CONSULT. A clinical example is presented which illustrates the use of CONSULT within the context of blood pressure management for secondary stroke prevention.

There has been much discussion of the right to explanation in the EU General Data Protection Regulation, and its existence, merits, and disadvantages. Implementing a right to explanation that opens the black box of algorithmic decision-making faces major legal and technical barriers. Explaining the functionality of complex algorithmic decision-making systems and their rationale in specific cases is a technically challenging problem. Some explanations may offer little meaningful information to data subjects, raising questions around their value. Explanations of automated decisions need not hinge on the general public understanding how algorithmic systems function. Even though such interpretability is of great importance and should be pursued, explanations can, in principle, be offered without opening the black box. Looking at explanations as a means to help a data subject act rather than merely understand, one could gauge the scope and content of explanations according to the specific goal or action they are intended to support. From the perspective of individuals affected by automated decision-making, we propose three aims for explanations: (1) to inform and help the individual understand why a particular decision was reached, (2) to provide grounds to contest the decision if the outcome is undesired, and (3) to understand what would need to change in order to receive a desired result in the future, based on the current decision-making model. We assess how each of these goals finds support in the GDPR. We suggest data controllers should offer a particular type of explanation, unconditional counterfactual explanations, to support these three aims. These counterfactual explanations describe the smallest change to the world that can be made to obtain a desirable outcome, or to arrive at the closest possible world, without needing to explain the internal logic of the system.

Online argumentation, particularly on popular public discussion boards and social media, is rich with fallacy-and bias-prone arguments. An artificially intelligent tool capable of identifying potential biases in online argumentation might be able to address this growing problem, but what would it take to develop such a tool? In this paper, we attempt to answer this question by carefully defining both argumentative biases and fallacies, and laying out some guidelines for automated bias detection. After laying out a roadmap and identifying current bottlenecks, we take some initial steps towards relieving these limitations through the creation of a dataset of personal and ad hominem attacks in comments. Our progress in this direction is summarized.

In the Internet of Everything environment, agents exchange messages, backing up and motivating their decisions. In this environment, validation of message validity, truthfulness, authenticity and consistency is essential. We formulate a problem of domain-independent assessment of argumentation validity based on rhetorical analysis of text. Argumentation structure is discovered in the form of discourse trees extended with edge labels for communicative actions. Extracted argumentation structures are then encoded as defeasible logic programs and are subject to dialectical analysis, to establish the validity of the main claim being communicated. We evaluate the accuracy of each step of this affect processing pipeline as well as overall performance.

British Prime Minister Theresa May said Russia's involvement is "highly likely," and she gave the country a deadline of midnight Tuesday to explain its actions in the case. She is reviewing a range of economic and diplomatic measures in retaliation for the assault with what she identified as the military-grade nerve agent Novichok.

Neural networks can answer a question about a photo and point to the evidence for their answer by annotating the image. How it works: To test the Pointing and Justification Explanation (PJ-X) model, researchers gathered data sets made up of pairs of photographs showing similar scenes, like different types of lunches. Then they came up with a question that has distinct answers for each photo ("Is this a healthy meal?"). What it does: After being trained on enough data, PJ-X could both answer the question using text ("No, it's a hot dog with lots of toppings"') and put a heat map over the photo to highlight the reasons behind the answer (the hot dog and its many toppings). Why it matters: Typical AIs are black boxes--good at identifying things, but with algorithmic logic that is opaque to humans.