We propose a novel approach to logic-based learning which generates assumption-based argumentation (ABA) frameworks from positive and negative examples, using a given background knowledge. These ABA frameworks can be mapped onto logic programs with negation as failure that may be non-stratified. Whereas existing argumentation-based methods learn exceptions to general rules by interpreting the exceptions as rebuttal attacks, our approach interprets them as undercutting attacks. Our learning technique is based on the use of transformation rules, including some adapted from logic program transformation rules (notably folding) as well as others, such as rote learning and assumption introduction. We present a general strategy that applies the transformation rules in a suitable order to learn stratified frameworks, and we also propose a variant that handles the non-stratified case. We illustrate the benefits of our approach with a number of examples, which show that, on one hand, we are able to easily reconstruct other logic-based learning approaches and, on the other hand, we can work out in a very simple and natural way problems that seem to be hard for existing techniques.

Several recent studies have elucidated why knowledge distillation (KD) improves model performance. However, few have researched the other advantages of KD in addition to its improving model performance. In this study, we have attempted to show that KD enhances the interpretability as well as the accuracy of models. We measured the number of concept detectors identified in network dissection for a quantitative comparison of model interpretability. We attributed the improvement in interpretability to the class-similarity information transferred from the teacher to student models. First, we confirmed the transfer of class-similarity information from the teacher to student model via logit distillation. Then, we analyzed how class-similarity information affects model interpretability in terms of its presence or absence and degree of similarity information. We conducted various quantitative and qualitative experiments and examined the results on different datasets, different KD methods, and according to different measures of interpretability. Our research showed that KD models by large models could be used more reliably in various fields.

A significant drawback of eXplainable Artificial Intelligence (XAI) approaches is the assumption of feature independence. This paper focuses on integrating causal knowledge in XAI methods to increase trust and help users assess explanations' quality. We propose a novel extension to a widely used local and model-agnostic explainer that explicitly encodes causal relationships in the data generated around the input instance to explain. Extensive experiments show that our method achieves superior performance comparing the initial one for both the fidelity in mimicking the black-box and the stability of the explanations.

Online discussion moderators must make ad-hoc decisions about whether the contributions of discussion participants are appropriate or should be removed to maintain civility. Existing research on offensive language and the resulting tools cover only one aspect among many involved in such decisions. The question of what is considered appropriate in a controversial discussion has not yet been systematically addressed. In this paper, we operationalize appropriate language in argumentation for the first time. In particular, we model appropriateness through the absence of flaws, grounded in research on argument quality assessment, especially in aspects from rhetoric. From these, we derive a new taxonomy of 14 dimensions that determine inappropriate language in online discussions. Building on three argument quality corpora, we then create a corpus of 2191 arguments annotated for the 14 dimensions. Empirical analyses support that the taxonomy covers the concept of appropriateness comprehensively, showing several plausible correlations with argument quality dimensions. Moreover, results of baseline approaches to assessing appropriateness suggest that all dimensions can be modeled computationally on the corpus.

Over the past decade explainable artificial intelligence has evolved from a predominantly technical discipline into a field that is deeply intertwined with social sciences. Insights such as human preference for contrastive -- more precisely, counterfactual -- explanations have played a major role in this transition, inspiring and guiding the research in computer science. Other observations, while equally important, have received much less attention. The desire of human explainees to communicate with artificial intelligence explainers through a dialogue-like interaction has been mostly neglected by the community. This poses many challenges for the effectiveness and widespread adoption of such technologies as delivering a single explanation optimised according to some predefined objectives may fail to engender understanding in its recipients and satisfy their unique needs given the diversity of human knowledge and intention. Using insights elaborated by Niklas Luhmann and, more recently, Elena Esposito we apply social systems theory to highlight challenges in explainable artificial intelligence and offer a path forward, striving to reinvigorate the technical research in this direction. This paper aims to demonstrate the potential of systems theoretical approaches to communication in understanding problems and limitations of explainable artificial intelligence.

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