The rapid growth of research in explainable artificial intelligence (XAI) follows on two substantial developments. First, the enormous application success of modern machine learning methods, especially deep and reinforcement learning, have created high expectations for industrial, commercial, and social value. Second, the emerging and growing concern for creating ethical and trusted AI systems, including compliance with regulatory principles to ensure transparency and trust. These two threads have created a kind of “perfect storm” of research activity, all motivated to create and deliver any set of tools and techniques to address the XAI demand. As some surveys of current XAI suggest, there is yet to appear a principled framework that respects the literature of explainability in the history of science and which provides a basis for the development of a framework for transparent XAI. We identify four foundational components, including the requirements for (1) explicit explanation knowledge representation, (2) delivery of alternative explanations, (3) adjusting explanations based on knowledge of the explainee, and (4) exploiting the advantage of interactive explanation. With those four components in mind, we intend to provide a strategic inventory of XAI requirements, demonstrate their connection to a basic history of XAI ideas, and then synthesize those ideas into a simple framework that can guide the design of AI systems that require XAI.

The challenge of information overload in the legal domain increases every day. The COLIEE competition has created four challenge tasks that are intended to encourage the development of systems and methods to alleviate some of that pressure: a case law retrieval (Task 1) and entailment (Task 2), and a statute law retrieval (Task 3) and entailment (Task 4). Here we describe our methods for Task 1 and Task 4. In Task 1, we used a sentence-transformer model to create a numeric representation for each case paragraph. We then created a histogram of the similarities between a query case and a candidate case. The histogram is used to build a binary classifier that decides whether a candidate case should be noticed or not. In Task 4, our approach relies on fine-tuning a pre-trained DeBERTa large language model (LLM) trained on SNLI and MultiNLI datasets. Our method for Task 4 was ranked third among eight participating teams in the COLIEE 2023 competition. For Task 4, We also compared the performance of the DeBERTa model with those of a knowledge distillation model and ensemble methods including Random Forest and Voting.

Interpretation methods for learned models used in natural language processing (NLP) applications usually provide support for local (specific) explanations, such as quantifying the contribution of each word to the predicted class. But they typically ignore the potential interaction amongst those word tokens. Unlike currently popular methods, we propose a deep model which uses feature attribution and identification of dependencies to support the learning of interpretable representations that will support creation of hierarchical explanations. In addition, hierarchical explanations provide a basis for visualizing how words and phrases are combined at different levels of abstraction, which enables end-users to better understand the prediction process of a deep network. Our study uses multiple wellknown datasets to demonstrate the effectiveness of our approach, and provides both automatic and human evaluation.

We present a method for explaining the image classification predictions of deep convolution neural networks, by highlighting the pixels in the image which influence the final class prediction. Our method requires the identification of a heuristic method to select parameters hypothesized to be most relevant in this prediction, and here we use Kullback-Leibler divergence to provide this focus. Overall, our approach helps in understanding and interpreting deep network predictions and we hope contributes to a foundation for such understanding of deep learning networks. In this brief paper, our experiments evaluate the performance of two popular networks in this context of interpretability.

The practical impact of deep learning on complex supervised learning problems has been significant, so much so that almost every Artificial Intelligence problem, or at least a portion thereof, has been somehow recast as a deep learning problem. The applications appeal is significant, but this appeal is increasingly challenged by what some call the challenge of explainability, or more generally the more traditional challenge of debuggability: if the outcomes of a deep learning process produce unexpected results (e.g., less than expected performance of a classifier), then there is little available in the way of theories or tools to help investigate the potential causes of such unexpected behavior, especially when this behavior could impact people's lives. We describe a preliminary framework to help address this issue, which we call "deep visual explanation" (DVE). "Deep," because it is the development and performance of deep neural network models that we want to understand. "Visual," because we believe that the most rapid insight into a complex multi-dimensional model is provided by appropriate visualization techniques, and "Explanation," because in the spectrum from instrumentation by inserting print statements to the abductive inference of explanatory hypotheses, we believe that the key to understanding deep learning relies on the identification and exposure of hypotheses about the performance behavior of a learned deep model. In the exposition of our preliminary framework, we use relatively straightforward image classification examples and a variety of choices on initial configuration of a deep model building scenario. By careful but not complicated instrumentation, we expose classification outcomes of deep models using visualization, and also show initial results for one potential application of interpretability.