Explainability of AI models is an important topic that can have a significant impact in all domains and applications from autonomous driving to healthcare. The existing approaches to explainable AI (XAI) are mainly limited to simple machine learning algorithms, and the research regarding the explainability-accuracy tradeoff is still in its infancy especially when we are concerned about complex machine learning techniques like neural networks and deep learning (DL). In this work, we introduce a new approach for complex models based on the co-relation impact which enhances the explainability considerably while also ensuring the accuracy at a high level. We propose approaches for both scenarios of independent features and dependent features. In addition, we study the uncertainty associated with features and output. Furthermore, we provide an upper bound of the computation complexity of our proposed approach for the dependent features. The complexity bound depends on the order of logarithmic of the number of observations which provides a reliable result considering the higher dimension of dependent feature space with a smaller number of observations.

Explaining the decisions of neural models is crucial for ensuring their trustworthiness at deployment time. Using Natural Language Explanations (NLEs) to justify a model's predictions has recently gained increasing interest. However, this approach usually demands large datasets of human-written NLEs for the ground-truth answers, which are expensive and potentially infeasible for some applications. For models to generate high-quality NLEs when only a few NLEs are available, the fine-tuning of Pre-trained Language Models (PLMs) in conjunction with prompt-based learning recently emerged. However, PLMs typically have billions of parameters, making fine-tuning expensive. We propose SparseFit, a sparse few-shot fine-tuning strategy that leverages discrete prompts to jointly generate predictions and NLEs. We experiment with SparseFit on the T5 model and four datasets and compare it against state-of-the-art parameter-efficient fine-tuning techniques. We perform automatic and human evaluations to assess the quality of the model-generated NLEs, finding that fine-tuning only 6.8% of the model parameters leads to competitive results for both the task performance and the quality of the NLEs.

An effective way to obtain different perspectives on any given topic is by conducting a debate, where participants argue for and against the topic. Here, we propose a novel debate framework for understanding and explaining a continuous image classifier's reasoning for making a particular prediction by modeling it as a multiplayer sequential zero-sum debate game. The contrastive nature of our framework encourages players to learn to put forward diverse arguments during the debates, picking up the reasoning trails missed by their opponents and highlighting any uncertainties in the classifier. Specifically, in our proposed setup, players propose arguments, drawn from the classifier's discretized latent knowledge, to support or oppose the classifier's decision. The resulting Visual Debates collect supporting and opposing features from the discretized latent space of the classifier, serving as explanations for the internal reasoning of the classifier towards its predictions. We demonstrate and evaluate (a practical realization of) our Visual Debates on the geometric SHAPE and MNIST datasets and on the high-resolution animal faces (AFHQ) dataset, along standard evaluation metrics for explanations (i.e. faithfulness and completeness) and novel, bespoke metrics for visual debates as explanations (consensus and split ratio).

Toxicity annotators and content moderators often default to mental shortcuts when making decisions. This can lead to subtle toxicity being missed, and seemingly toxic but harmless content being over-detected. We introduce BiasX, a framework that enhances content moderation setups with free-text explanations of statements' implied social biases, and explore its effectiveness through a large-scale crowdsourced user study. We show that indeed, participants substantially benefit from explanations for correctly identifying subtly (non-)toxic content. The quality of explanations is critical: imperfect machine-generated explanations (+2.4% on hard toxic examples) help less compared to expert-written human explanations (+7.2%). Our results showcase the promise of using free-text explanations to encourage more thoughtful toxicity moderation.

Understanding the internal reasoning behind the predictions of machine learning systems is increasingly vital, given their rising adoption and acceptance. While previous approaches, such as LIME, generate algorithmic explanations by attributing importance to input features for individual examples, recent research indicates that practitioners prefer examining language explanations that explain sub-groups of examples. In this paper, we introduce MaNtLE, a model-agnostic natural language explainer that analyzes multiple classifier predictions and generates faithful natural language explanations of classifier rationale for structured classification tasks. MaNtLE uses multi-task training on thousands of synthetic classification tasks to generate faithful explanations. Simulated user studies indicate that, on average, MaNtLE-generated explanations are at least 11% more faithful compared to LIME and Anchors explanations across three tasks. Human evaluations demonstrate that users can better predict model behavior using explanations from MaNtLE compared to other techniques

Human-annotated labels and explanations are critical for training explainable NLP models. However, unlike human-annotated labels whose quality is easier to calibrate (e.g., with a majority vote), human-crafted free-form explanations can be quite subjective. Before blindly using them as ground truth to train ML models, a vital question needs to be asked: How do we evaluate a human-annotated explanation's quality? In this paper, we build on the view that the quality of a human-annotated explanation can be measured based on its helpfulness (or impairment) to the ML models' performance for the desired NLP tasks for which the annotations were collected. In comparison to the commonly used Simulatability score, we define a new metric that can take into consideration the helpfulness of an explanation for model performance at both fine-tuning and inference. With the help of a unified dataset format, we evaluated the proposed metric on five datasets (e.g., e-SNLI) against two model architectures (T5 and BART), and the results show that our proposed metric can objectively evaluate the quality of human-annotated explanations, while Simulatability falls short.

The term explanation in artificial intelligence (AI) is often conflated with the concepts of interpretability and explainable AI (XAI), but there are important distinctions to be made. Miller (2019) defines interpretability and XAI as the process of building AI systems that humans can understand. In other words, by design, the AI's decision-making process is inherently transparent to a human. In contrast, explicitly explaining the decision-making to an arbitrary human is explanation generation. The latter is the subject of this paper. More specifically, we are working towards developing a formal framework for the automated generation and assessment of explanations. Firstly, some key terminology: an explanation is generated through a dialectical interaction whereby one agent, the explainer, seeks to'explain' some phenomenon, called the explanandum, to another agent, the explainee. In this article, we propose a novel measure of explanatory effectiveness that can be used to motivate artificial agents to generate good explanations (e.g. in the form of a reward signal), or to analyse the behaviours of existing communicating agents. We then define explanation games as cooperative games where two (or more) agents seek to maximise the effectiveness measure.

As artificial intelligence (AI) becomes more prevalent there is a growing demand from regulators to accompany decisions made by such systems with explanations. However, a persistent gap exists between the need to execute a meaningful right to explanation vs. the ability of Machine Learning systems to deliver on such a legal requirement. The regulatory appeal towards "a right to explanation" of AI systems can be attributed to the significant role of explanations, part of the notion called reason-giving, in law. Therefore, in this work we examine reason-giving's purposes in law to analyze whether reasons provided by end-user Explainability can adequately fulfill them. We find that reason-giving's legal purposes include: (a) making a better and more just decision, (b) facilitating due-process, (c) authenticating human agency, and (d) enhancing the decision makers' authority. Using this methodology, we demonstrate end-user Explainabilty's inadequacy to fulfil reason-giving's role in law, given reason-giving's functions rely on its impact over a human decision maker. Thus, end-user Explainability fails, or is unsuitable, to fulfil the first, second and third legal function. In contrast we find that end-user Explainability excels in the fourth function, a quality which raises serious risks considering recent end-user Explainability research trends, Large Language Models' capabilities, and the ability to manipulate end-users by both humans and machines. Hence, we suggest that in some cases the right to explanation of AI systems could bring more harm than good to end users. Accordingly, this study carries some important policy ramifications, as it calls upon regulators and Machine Learning practitioners to reconsider the widespread pursuit of end-user Explainability and a right to explanation of AI systems.

After introducing the scope of this paper, we start by discussing what an "explanation" really is. We then move on to discuss some of the existing approaches to XAI and build a taxonomy of the most popular methods. Next, we also look at a few applications of these and other XAI techniques in four primary domains: finance, autonomous driving, healthcare and manufacturing. We end by introducing a promising discipline, "Explanation Engineering," which includes a systematic approach for designing explainability into AI systems.

In recent years, understanding the decision-making process of black-box models has become not only a legal requirement but also an additional way to assess their performance. However, the state of the art post-hoc interpretation approaches rely on synthetic data generation. This introduces uncertainty and can hurt the reliability of the interpretations. Furthermore, they tend to produce explanations that apply to only very few data points. This makes the explanations brittle and limited in scope. Finally, they provide scores that have no direct verifiable meaning. In this paper, we present BELLA, a deterministic model-agnostic post-hoc approach for explaining the individual predictions of regression black-box models. BELLA provides explanations in the form of a linear model trained in the feature space. Thus, its coefficients can be used directly to compute the predicted value from the feature values. Furthermore, BELLA maximizes the size of the neighborhood to which the linear model applies, so that the explanations are accurate, simple, general, and robust. BELLA can produce both factual and counterfactual explanations. Our user study confirms the importance of the desiderata we optimize, and our experiments show that BELLA outperforms the state-of-the-art approaches on these desiderata.