Research Papers

The remarkable success of Artificial Intelligence in advancing automated decision-making is evident both in academia and industry. Within the plethora of applications, ranking systems hold significant importance in various domains. This paper advocates for the application of a specific form of Explainable AI -- namely, contrastive explanations -- as particularly well-suited for addressing ranking problems. This approach is especially potent when combined with an Evaluative AI methodology, which conscientiously evaluates both positive and negative aspects influencing a potential ranking. Therefore, the present work introduces Evaluative Item-Contrastive Explanations tailored for ranking systems and illustrates its application and characteristics through an experiment conducted on publicly available data.

Explainability is a vital aspect of modern AI for real-world impact and usability. The main objective of this paper is to emphasise the need to understand the predictions of Computer Vision models, specifically Convolutional Neural Network (CNN) models. Existing methods for explaining CNN predictions are largely based on Gradient-weighted Class Activation Maps (Grad-CAM) and focus solely on a single target class; this assumption about the target class selection neglects a large portion of the predictor CNN's prediction process. In this paper, we present an exhaustive methodology, called Fused Multi-class Gradient-weighted Class Activation Map (FM-G-CAM), that considers multiple top-predicted classes and provides a holistic explanation of the predictor CNN's rationale. We also provide a detailed mathematical and algorithmic description of our method. Furthermore, alongside a concise comparison of existing methods, we compare FM-G-CAM with Grad-CAM, quantitatively and qualitatively highlighting its benefits through real-world practical use cases. Finally, we present an open-source Python library with an FM-G-CAM implementation to conveniently generate saliency maps for CNN-based model predictions.

SoUnD Framework: Analyzing (So)cial Representation in (Un)structured (D)ata

Mark Díaz, Sunipa Dev, Emily Reif +2

The unstructured nature of data used in foundation model development is a challenge to systematic analyses for making data use and documentation decisions. From a Responsible AI perspective, these decisions often rely upon understanding how people are represented in data. We propose a framework designed to guide analysis of human representation in unstructured data and identify downstream risks. We apply the framework in two toy examples using the Common Crawl web text corpus (C4) and LAION-400M. We also propose a set of hypothetical action steps in service of dataset use, development, and documentation.

Responsible AI Considerations in Text Summarization Research: A Review of Current Practices

Yu Lu Liu, Meng Cao, Su Lin Blodgett +3

AI and NLP publication venues have increasingly encouraged researchers to reflect on possible ethical considerations, adverse impacts, and other responsible AI issues their work might engender. However, for specific NLP tasks our understanding of how prevalent such issues are, or when and why these issues are likely to arise, remains limited. Focusing on text summarization -- a common NLP task largely overlooked by the responsible AI community -- we examine research and reporting practices in the current literature. We conduct a multi-round qualitative analysis of 333 summarization papers from the ACL Anthology published between 2020-2022. We focus on how, which, and when responsible AI issues are covered, which relevant stakeholders are considered, and mismatches between stated and realized research goals. We also discuss current evaluation practices and consider how authors discuss the limitations of both prior work and their own work. Overall, we find that relatively few papers engage with possible stakeholders or contexts of use, which limits their consideration of potential downstream adverse impacts or other responsible AI issues. Based on our findings, we make recommendations on concrete practices and research directions.

Explaining Search Result Stances to Opinionated People

Z. Wu, T. Draws, F. Cau +3

People use web search engines to find information before forming opinions, which can lead to practical decisions with different levels of impact. The cognitive effort of search can leave opinionated users vulnerable to cognitive biases, e.g., the confirmation bias. In this paper, we investigate whether stance labels and their explanations can help users consume more diverse search results. We automatically classify and label search results on three topics (i.e., intellectual property rights, school uniforms, and atheism) as against, neutral, and in favor, and generate explanations for these labels. In a user study (N =203), we then investigate whether search result stance bias (balanced vs biased) and the level of explanation (plain text, label only, label and explanation) influence the diversity of search results clicked. We find that stance labels and explanations lead to a more diverse search result consumption. However, we do not find evidence for systematic opinion change among users in this context. We believe these results can help designers of search engines to make more informed design decisions.

We propose a Holistic Return on Ethics (HROE) framework for understanding the return on organizational investments in artificial intelligence (AI) ethics efforts. This framework is useful for organizations that wish to quantify the return for their investment decisions. The framework identifies the direct economic returns of such investments, the indirect paths to return through intangibles associated with organizational reputation, and real options associated with capabilities. The holistic framework ultimately provides organizations with the competency to employ and justify AI ethics investments.

In this work, we propose a methodology for investigating the use of semantic attention to enhance the explainability of Graph Neural Network (GNN)-based models. Graph Deep Learning (GDL) has emerged as a promising field for tasks like scene interpretation, leveraging flexible graph structures to concisely describe complex features and relationships. As traditional explainability methods used in eXplainable AI (XAI) cannot be directly applied to such structures, graph-specific approaches are introduced. Attention has been previously employed to estimate the importance of input features in GDL, however, the fidelity of this method in generating accurate and consistent explanations has been questioned. To evaluate the validity of using attention weights as feature importance indicators, we introduce semantically-informed perturbations and correlate predicted attention weights with the accuracy of the model. Our work extends existing attention-based graph explainability methods by analysing the divergence in the attention distributions in relation to semantically sorted feature sets and the behaviour of a GNN model, efficiently estimating feature importance. We apply our methodology on a lidar pointcloud estimation model successfully identifying key semantic classes that contribute to enhanced performance, effectively generating reliable post-hoc semantic explanations.

Precise Benchmarking of Explainable AI Attribution Methods

Rafaël Brandt, Daan Raatjens, Georgi Gaydadjiev

The rationale behind a deep learning model's output is often difficult to understand by humans. EXplainable AI (XAI) aims at solving this by developing methods that improve interpretability and explainability of machine learning models. Reliable evaluation metrics are needed to assess and compare different XAI methods. We propose a novel evaluation approach for benchmarking state-of-the-art XAI attribution methods. Our proposal consists of a synthetic classification model accompanied by its derived ground truth explanations allowing high precision representation of input nodes contributions. We also propose new high-fidelity metrics to quantify the difference between explanations of the investigated XAI method and those derived from the synthetic model. Our metrics allow assessment of explanations in terms of precision and recall separately. Also, we propose metrics to independently evaluate negative or positive contributions of inputs. Our proposal provides deeper insights into XAI methods output. We investigate our proposal by constructing a synthetic convolutional image classification model and benchmarking several widely used XAI attribution methods using our evaluation approach. We compare our results with established prior XAI evaluation metrics. By deriving the ground truth directly from the constructed model in our method, we ensure the absence of bias, e.g., subjective either based on the training set. Our experimental results provide novel insights into the performance of Guided-Backprop and Smoothgrad XAI methods that are widely in use. Both have good precision and recall scores among positively contributing pixels (0.7, 0.76 and 0.7, 0.77, respectively), but poor precision scores among negatively contributing pixels (0.44, 0.61 and 0.47, 0.75, resp.). The recall scores in the latter case remain close. We show that our metrics are among the fastest in terms of execution time.

Images are loaded with semantic information that pertains to real-world ontologies: dog breeds share mammalian similarities, food pictures are often depicted in domestic environments, and so on. However, when training machine learning models for image classification, the relative similarities amongst object classes are commonly paired with one-hot-encoded labels. According to this logic, if an image is labelled as 'spoon', then 'tea-spoon' and 'shark' are equally wrong in terms of training loss. To overcome this limitation, we explore the integration of additional goals that reflect ontological and semantic knowledge, improving model interpretability and trustworthiness. We suggest a generic approach that allows to derive an additional loss term starting from any kind of semantic information about the classification label. First, we show how to apply our approach to ontologies and word embeddings, and discuss how the resulting information can drive a supervised learning process. Second, we use our semantically enriched loss to train image classifiers, and analyse the trade-offs between accuracy, mistake severity, and learned internal representations. Finally, we discuss how this approach can be further exploited in terms of explainability and adversarial robustness. Code repository: https://github.com/S1M0N38/semantic-encodings

With the rising necessity of explainable artificial intelligence (XAI), we see an increase in task-dependent XAI methods on varying abstraction levels. XAI techniques on a global level explain model behavior and on a local level explain sample predictions. We propose a visual analytics workflow to support seamless transitions between global and local explanations, focusing on attributions and counterfactuals on time series classification. In particular, we adapt local XAI techniques (attributions) that are developed for traditional datasets (images, text) to analyze time series classification, a data type that is typically less intelligible to humans. To generate a global overview, we apply local attribution methods to the data, creating explanations for the whole dataset. These explanations are projected onto two dimensions, depicting model behavior trends, strategies, and decision boundaries. To further inspect the model decision-making as well as potential data errors, a what-if analysis facilitates hypothesis generation and verification on both the global and local levels. We constantly collected and incorporated expert user feedback, as well as insights based on their domain knowledge, resulting in a tailored analysis workflow and system that tightly integrates time series transformations into explanations. Lastly, we present three use cases, verifying that our technique enables users to (1)~explore data transformations and feature relevance, (2)~identify model behavior and decision boundaries, as well as, (3)~the reason for misclassifications.

Machine Learning (ML) systems, particularly when deployed in high-stakes domains, are deeply consequential. They can exacerbate existing inequities, create new modes of discrimination, and reify outdated social constructs. Accordingly, the social context (i.e. organisations, teams, cultures) in which ML systems are developed is a site of active research for the field of AI ethics, and intervention for policymakers. This paper focuses on one aspect of social context that is often overlooked: interactions between practitioners and the tools they rely on, and the role these interactions play in shaping ML practices and the development of ML systems. In particular, through an empirical study of questions asked on the Stack Exchange forums, the use of interactive computing platforms (e.g. Jupyter Notebook and Google Colab) in ML practices is explored. I find that interactive computing platforms are used in a host of learning and coordination practices, which constitutes an infrastructural relationship between interactive computing platforms and ML practitioners. I describe how ML practices are co-evolving alongside the development of interactive computing platforms, and highlight how this risks making invisible aspects of the ML life cycle that AI ethics researchers' have demonstrated to be particularly salient for the societal impact of deployed ML systems.

The application of Algorithmic Recourse in decision-making is a promising field that offers practical solutions to reverse unfavorable decisions. However, the inability of these methods to consider potential dependencies among variables poses a significant challenge due to the assumption of feature independence. Recent advancements have incorporated knowledge of causal dependencies, thereby enhancing the quality of the recommended recourse actions. Despite these improvements, the inability to incorporate the temporal dimension remains a significant limitation of these approaches. This is particularly problematic as identifying and addressing the root causes of undesired outcomes requires understanding time-dependent relationships between variables. In this work, we motivate the need to integrate the temporal dimension into causal algorithmic recourse methods to enhance recommendations' plausibility and reliability. The experimental evaluation highlights the significance of the role of time in this field.