Research Papers

A Human-Grounded Evaluation of SHAP for Alert Processing

Hilde J. P. Weerts, Werner van Ipenburg, Mykola Pechenizkiy

In the past years, many new explanation methods have been proposed to achieve interpretability of machine learning predictions. However, the utility of these methods in practical applications has not been researched extensively. In this paper we present the results of a human-grounded evaluation of SHAP, an explanation method that has been well-received in the XAI and related communities. In particular, we study whether this local model-agnostic explanation method can be useful for real human domain experts to assess the correctness of positive predictions, i.e. alerts generated by a classifier. We performed experimentation with three different groups of participants (159 in total), who had basic knowledge of explainable machine learning. We performed a qualitative analysis of recorded reflections of experiment participants performing alert processing with and without SHAP information. The results suggest that the SHAP explanations do impact the decision-making process, although the model's confidence score remains to be a leading source of evidence. We statistically test whether there is a significant difference in task utility metrics between tasks for which an explanation was available and tasks in which it was not provided. As opposed to common intuitions, we did not find a significant difference in alert processing performance when a SHAP explanation is available compared to when it is not.

Information fusion is an essential part of numerous engineering systems and biological functions, e.g., human cognition. Fusion occurs at many levels, ranging from the low-level combination of signals to the high-level aggregation of heterogeneous decision-making processes. While the last decade has witnessed an explosion of research in deep learning, fusion in neural networks has not observed the same revolution. Specifically, most neural fusion approaches are ad hoc, are not understood, are distributed versus localized, and/or explainability is low (if present at all). Herein, we prove that the fuzzy Choquet integral (ChI), a powerful nonlinear aggregation function, can be represented as a multi-layer network, referred to hereafter as ChIMP. We also put forth an improved ChIMP (iChIMP) that leads to a stochastic gradient descent-based optimization in light of the exponential number of ChI inequality constraints. An additional benefit of ChIMP/iChIMP is that it enables eXplainable AI (XAI). Synthetic validation experiments are provided and iChIMP is applied to the fusion of a set of heterogeneous architecture deep models in remote sensing. We show an improvement in model accuracy and our previously established XAI indices shed light on the quality of our data, model, and its decisions.

LLM Voting: Human Choices and AI Collective Decision Making

Joshua C. Yang, Damian Dailisan, Marcin Korecki +2

This paper investigates the voting behaviors of Large Language Models (LLMs), specifically GPT-4 and LLaMA-2, their biases, and how they align with human voting patterns. Our methodology involved using a dataset from a human voting experiment to establish a baseline for human preferences and conducting a corresponding experiment with LLM agents. We observed that the choice of voting methods and the presentation order influenced LLM voting outcomes. We found that varying the persona can reduce some of these biases and enhance alignment with human choices. While the Chain-of-Thought approach did not improve prediction accuracy, it has potential for AI explainability in the voting process. We also identified a trade-off between preference diversity and alignment accuracy in LLMs, influenced by different temperature settings. Our findings indicate that LLMs may lead to less diverse collective outcomes and biased assumptions when used in voting scenarios, emphasizing the need for cautious integration of LLMs into democratic processes.

As the use of Blockchain for digital payments continues to rise in popularity, it also becomes susceptible to various malicious attacks. Successfully detecting anomalies within Blockchain transactions is essential for bolstering trust in digital payments. However, the task of anomaly detection in Blockchain transaction data is challenging due to the infrequent occurrence of illicit transactions. Although several studies have been conducted in the field, a limitation persists: the lack of explanations for the model's predictions. This study seeks to overcome this limitation by integrating eXplainable Artificial Intelligence (XAI) techniques and anomaly rules into tree-based ensemble classifiers for detecting anomalous Bitcoin transactions. The Shapley Additive exPlanation (SHAP) method is employed to measure the contribution of each feature, and it is compatible with ensemble models. Moreover, we present rules for interpreting whether a Bitcoin transaction is anomalous or not. Additionally, we have introduced an under-sampling algorithm named XGBCLUS, designed to balance anomalous and non-anomalous transaction data. This algorithm is compared against other commonly used under-sampling and over-sampling techniques. Finally, the outcomes of various tree-based single classifiers are compared with those of stacking and voting ensemble classifiers. Our experimental results demonstrate that: (i) XGBCLUS enhances TPR and ROC-AUC scores compared to state-of-the-art under-sampling and over-sampling techniques, and (ii) our proposed ensemble classifiers outperform traditional single tree-based machine learning classifiers in terms of accuracy, TPR, and FPR scores.

Artificial Intelligence (AI) solutions and technologies are being increasingly adopted in smart systems context, however, such technologies are continuously concerned with ethical uncertainties. Various guidelines, principles, and regulatory frameworks are designed to ensure that AI technologies bring ethical well-being. However, the implications of AI ethics principles and guidelines are still being debated. To further explore the significance of AI ethics principles and relevant challenges, we conducted a survey of 99 representative AI practitioners and lawmakers (e.g., AI engineers, lawyers) from twenty countries across five continents. To the best of our knowledge, this is the first empirical study that encapsulates the perceptions of two different types of population (AI practitioners and lawmakers) and the study findings confirm that transparency, accountability, and privacy are the most critical AI ethics principles. On the other hand, lack of ethical knowledge, no legal frameworks, and lacking monitoring bodies are found the most common AI ethics challenges. The impact analysis of the challenges across AI ethics principles reveals that conflict in practice is a highly severe challenge. Moreover, the perceptions of practitioners and lawmakers are statistically correlated with significant differences for particular principles (e.g. fairness, freedom) and challenges (e.g. lacking monitoring bodies, machine distortion). Our findings stimulate further research, especially empowering existing capability maturity models to support the development and quality assessment of ethics-aware AI systems.

Interpretable Data-Based Explanations for Fairness Debugging

Romila Pradhan, Jiongli Zhu, Boris Glavic +1

A wide variety of fairness metrics and eXplainable Artificial Intelligence (XAI) approaches have been proposed in the literature to identify bias in machine learning models that are used in critical real-life contexts. However, merely reporting on a model's bias, or generating explanations using existing XAI techniques is insufficient to locate and eventually mitigate sources of bias. We introduce Gopher, a system that produces compact, interpretable and causal explanations for bias or unexpected model behavior by identifying coherent subsets of the training data that are root-causes for this behavior. Specifically, we introduce the concept of causal responsibility that quantifies the extent to which intervening on training data by removing or updating subsets of it can resolve the bias. Building on this concept, we develop an efficient approach for generating the top-k patterns that explain model bias that utilizes techniques from the machine learning (ML) community to approximate causal responsibility and uses pruning rules to manage the large search space for patterns. Our experimental evaluation demonstrates the effectiveness of Gopher in generating interpretable explanations for identifying and debugging sources of bias.

In this paper, we investigate the computational intelligibility of Boolean classifiers, characterized by their ability to answer XAI queries in polynomial time. The classifiers under consideration are decision trees, DNF formulae, decision lists, decision rules, tree ensembles, and Boolean neural nets. Using 9 XAI queries, including both explanation queries and verification queries, we show the existence of large intelligibility gap between the families of classifiers. On the one hand, all the 9 XAI queries are tractable for decision trees. On the other hand, none of them is tractable for DNF formulae, decision lists, random forests, boosted decision trees, Boolean multilayer perceptrons, and binarized neural networks.

AI Governance in Higher Education: Case Studies of Guidance at Big Ten Universities

Chuhao Wu, He Zhang, John M. Carroll

Generative AI has drawn significant attention from stakeholders in higher education. As it introduces new opportunities for personalized learning and tutoring support, it simultaneously poses challenges to academic integrity and leads to ethical issues. Consequently, governing responsible AI usage within higher education institutions (HEIs) becomes increasingly important. Leading universities have already published guidelines on Generative AI, with most attempting to embrace this technology responsibly. This study provides a new perspective by focusing on strategies for responsible AI governance as demonstrated in these guidelines. Through a case study of 14 prestigious universities in the United States, we identified the multi-unit governance of AI, the role-specific governance of AI, and the academic characteristics of AI governance from their AI guidelines. The strengths and potential limitations of these strategies and characteristics are discussed. The findings offer practical implications for guiding responsible AI usage in HEIs and beyond.

Advances in Generative Artificial Intelligence (AI) are resulting in AI-generated media output that is (nearly) indistinguishable from human-created content. This can drastically impact users and the media sector, especially given global risks of misinformation. While the currently discussed European AI Act aims at addressing these risks through Article 52's AI transparency obligations, its interpretation and implications remain unclear. In this early work, we adopt a participatory AI approach to derive key questions based on Article 52's disclosure obligations. We ran two workshops with researchers, designers, and engineers across disciplines (N=16), where participants deconstructed Article 52's relevant clauses using the 5W1H framework. We contribute a set of 149 questions clustered into five themes and 18 sub-themes. We believe these can not only help inform future legal developments and interpretations of Article 52, but also provide a starting point for Human-Computer Interaction research to (re-)examine disclosure transparency from a human-centered AI lens.

Recent advances in deep learning have improved the performance of many Natural Language Processing (NLP) tasks such as translation, question-answering, and text classification. However, this improvement comes at the expense of model explainability. Black-box models make it difficult to understand the internals of a system and the process it takes to arrive at an output. Numerical (LIME, Shapley) and visualization (saliency heatmap) explainability techniques are helpful; however, they are insufficient because they require specialized knowledge. These factors led rationalization to emerge as a more accessible explainable technique in NLP. Rationalization justifies a model's output by providing a natural language explanation (rationale). Recent improvements in natural language generation have made rationalization an attractive technique because it is intuitive, human-comprehensible, and accessible to non-technical users. Since rationalization is a relatively new field, it is disorganized. As the first survey, rationalization literature in NLP from 2007-2022 is analyzed. This survey presents available methods, explainable evaluations, code, and datasets used across various NLP tasks that use rationalization. Further, a new subfield in Explainable AI (XAI), namely, Rational AI (RAI), is introduced to advance the current state of rationalization. A discussion on observed insights, challenges, and future directions is provided to point to promising research opportunities.

A Transparency Index Framework for AI in Education

Muhammad Ali Chaudhry, Mutlu Cukurova, Rose Luckin

Numerous AI ethics checklists and frameworks have been proposed focusing on different dimensions of ethical AI such as fairness, explainability, and safety. Yet, no such work has been done on developing transparent AI systems for real-world educational scenarios. This paper presents a Transparency Index framework that has been iteratively co-designed with different stakeholders of AI in education, including educators, ed-tech experts, and AI practitioners. We map the requirements of transparency for different categories of stakeholders of AI in education and demonstrate that transparency considerations are embedded in the entire AI development process from the data collection stage until the AI system is deployed in the real world and iteratively improved. We also demonstrate how transparency enables the implementation of other ethical AI dimensions in Education like interpretability, accountability, and safety. In conclusion, we discuss the directions for future research in this newly emerging field. The main contribution of this study is that it highlights the importance of transparency in developing AI-powered educational technologies and proposes an index framework for its conceptualization for AI in education.

Stable operation of the electrical power system requires the power grid frequency to stay within strict operational limits. With millions of consumers and thousands of generators connected to a power grid, detailed human-build models can no longer capture the full dynamics of this complex system. Modern machine learning algorithms provide a powerful alternative for system modelling and prediction, but the intrinsic black-box character of many models impedes scientific insights and poses severe security risks. Here, we show how eXplainable AI (XAI) alleviates these problems by revealing critical dependencies and influences on the power grid frequency. We accurately predict frequency stability indicators (such as RoCoF and Nadir) for three major European synchronous areas and identify key features that determine the power grid stability. Load ramps, specific generation ramps but also prices and forecast errors are central to understand and stabilize the power grid.