Research Papers

Earthquake-induced liquefaction can cause substantial lateral spreading, posing threats to infrastructure. Machine learning (ML) can improve lateral spreading prediction models by capturing complex soil characteristics and site conditions. However, the "black box" nature of ML models can hinder their adoption in critical decision-making. This study addresses this limitation by using SHapley Additive exPlanations (SHAP) to interpret an eXtreme Gradient Boosting (XGB) model for lateral spreading prediction, trained on data from the 2011 Christchurch Earthquake. SHAP analysis reveals the factors driving the model's predictions, enhancing transparency and allowing for comparison with established engineering knowledge. The results demonstrate that the XGB model successfully identifies the importance of soil characteristics derived from Cone Penetration Test (CPT) data in predicting lateral spreading, validating its alignment with domain understanding. This work highlights the value of explainable machine learning for reliable and informed decision-making in geotechnical engineering and hazard assessment.

Prior research has revealed that certain abstract concepts are linearly represented as directions in the representation space of LLMs, predominantly centered around English. In this paper, we extend this investigation to a multilingual context, with a specific focus on human values-related concepts (i.e., value concepts) due to their significance for AI safety. Through our comprehensive exploration covering 7 types of human values, 16 languages and 3 LLM series with distinct multilinguality (e.g., monolingual, bilingual and multilingual), we first empirically confirm the presence of value concepts within LLMs in a multilingual format. Further analysis on the cross-lingual characteristics of these concepts reveals 3 traits arising from language resource disparities: cross-lingual inconsistency, distorted linguistic relationships, and unidirectional cross-lingual transfer between high- and low-resource languages, all in terms of value concepts. Moreover, we validate the feasibility of cross-lingual control over value alignment capabilities of LLMs, leveraging the dominant language as a source language. Ultimately, recognizing the significant impact of LLMs' multilinguality on our results, we consolidate our findings and provide prudent suggestions on the composition of multilingual data for LLMs pre-training.

Language model alignment has become an important component of AI safety, allowing safe interactions between humans and language models, by enhancing desired behaviors and inhibiting undesired ones. It is often done by tuning the model or inserting preset aligning prompts. Recently, representation engineering, a method which alters the model's behavior via changing its representations post-training, was shown to be effective in aligning LLMs (Zou et al., 2023a). Representation engineering yields gains in alignment oriented tasks such as resistance to adversarial attacks and reduction of social biases, but was also shown to cause a decrease in the ability of the model to perform basic tasks. In this paper we study the tradeoff between the increase in alignment and decrease in helpfulness of the model. We propose a theoretical framework which provides bounds for these two quantities, and demonstrate their relevance empirically. First, we find that under the conditions of our framework, alignment can be guaranteed with representation engineering, and at the same time that helpfulness is harmed in the process. Second, we show that helpfulness is harmed quadratically with the norm of the representation engineering vector, while the alignment increases linearly with it, indicating a regime in which it is efficient to use representation engineering. We validate our findings empirically, and chart the boundaries to the usefulness of representation engineering for alignment.

Sixth-generation (6G) network slicing is the backbone of future communications systems. It inaugurates the era of extreme ultra-reliable and low-latency communication (xURLLC) and pervades the digitalization of the various vertical immersive use cases. Since 6G inherently underpins artificial intelligence (AI), we propose a systematic and standalone slice termed SliceOps that is natively embedded in the 6G architecture, which gathers and manages the whole AI lifecycle through monitoring, re-training, and deploying the machine learning (ML) models as a service for the 6G slices. By leveraging machine learning operations (MLOps) in conjunction with eXplainable AI (XAI), SliceOps strives to cope with the opaqueness of black-box AI using explanation-guided reinforcement learning (XRL) to fulfill transparency, trustworthiness, and interpretability in the network slicing ecosystem. This article starts by elaborating on the architectural and algorithmic aspects of SliceOps. Then, the deployed cloud-native SliceOps working is exemplified via a latency-aware resource allocation problem. The deep RL (DRL)-based SliceOps agents within slices provide AI services aiming to allocate optimal radio resources and impede service quality degradation. Simulation results demonstrate the effectiveness of SliceOps-driven slicing. The article discusses afterward the SliceOps challenges and limitations. Finally, the key open research directions corresponding to the proposed approach are identified.

Assessments of algorithmic bias in large language models (LLMs) are generally catered to uncovering systemic discrimination based on protected characteristics such as sex and ethnicity. However, there are over 180 documented cognitive biases that pervade human reasoning and decision making that are routinely ignored when discussing the ethical complexities of AI. We demonstrate the presence of these cognitive biases in LLMs and discuss the implications of using biased reasoning under the guise of expertise. We call for stronger education, risk management, and continued research as widespread adoption of this technology increases. Finally, we close with a set of best practices for when and how to employ this technology as widespread adoption continues to grow.

Due to convenience, open-source software is widely used. For beneficial reasons, open-source maintainers often fix the vulnerabilities silently, exposing their users unaware of the updates to threats. Previous works all focus on black-box binary detection of the silent dependency alerts that suffer from high false-positive rates. Open-source software users need to analyze and explain AI prediction themselves. Explainable AI becomes remarkable as a complementary of black-box AI models, providing details in various forms to explain AI decisions. Noticing there is still no technique that can discover silent dependency alert on time, in this work, we propose a framework using an encoder-decoder model with a binary detector to provide explainable silent dependency alert prediction. Our model generates 4 types of vulnerability key aspects including vulnerability type, root cause, attack vector, and impact to enhance the trustworthiness and users' acceptance to alert prediction. By experiments with several models and inputs, we confirm CodeBERT with both commit messages and code changes achieves the best results. Our user study shows that explainable alert predictions can help users find silent dependency alert more easily than black-box predictions. To the best of our knowledge, this is the first research work on the application of Explainable AI in silent dependency alert prediction, which opens the door of the related domains.

Attribution-based XAI Methods in Computer Vision: A Review

Kumar Abhishek, Deeksha Kamath

The advancements in deep learning-based methods for visual perception tasks have seen astounding growth in the last decade, with widespread adoption in a plethora of application areas from autonomous driving to clinical decision support systems. Despite their impressive performance, these deep learning-based models remain fairly opaque in their decision-making process, making their deployment in human-critical tasks a risky endeavor. This in turn makes understanding the decisions made by these models crucial for their reliable deployment. Explainable AI (XAI) methods attempt to address this by offering explanations for such black-box deep learning methods. In this paper, we provide a comprehensive survey of attribution-based XAI methods in computer vision and review the existing literature for gradient-based, perturbation-based, and contrastive methods for XAI, and provide insights on the key challenges in developing and evaluating robust XAI methods.

Generative AI based art has proliferated in the past year, with increasingly impressive use cases from generating fake human faces to the creation of systems that can generate thousands of artistic images from text prompts - some of these images have even been "good" enough to win accolades from qualified judges. In this paper, we explore how Generative Models have impacted artistry, not only from a qualitative point of view, but also from an angle of exploitation of artists -- both via plagiarism, where models are trained on their artwork without permission, and via profit shifting, where profits in the art market have shifted from art creators to model owners. However, we posit that if deployed responsibly, AI generative models have the possibility of being a positive, new modality in art that does not displace or harm existing artists.

Towards Responsible AI for Financial Transactions

Charl Maree, Jan Erik Modal, Christian W. Omlin

The application of AI in finance is increasingly dependent on the principles of responsible AI. These principles - explainability, fairness, privacy, accountability, transparency and soundness form the basis for trust in future AI systems. In this study, we address the first principle by providing an explanation for a deep neural network that is trained on a mixture of numerical, categorical and textual inputs for financial transaction classification. The explanation is achieved through (1) a feature importance analysis using Shapley additive explanations (SHAP) and (2) a hybrid approach of text clustering and decision tree classifiers. We then test the robustness of the model by exposing it to a targeted evasion attack, leveraging the knowledge we gained about the model through the extracted explanation.

Ensuring fairness in artificial intelligence (AI) is important to counteract bias and discrimination in far-reaching applications. Recent work has started to investigate how humans judge fairness and how to support machine learning (ML) experts in making their AI models fairer. Drawing inspiration from an Explainable AI (XAI) approach called \emph{explanatory debugging} used in interactive machine learning, our work explores designing interpretable and interactive human-in-the-loop interfaces that allow ordinary end-users without any technical or domain background to identify potential fairness issues and possibly fix them in the context of loan decisions. Through workshops with end-users, we co-designed and implemented a prototype system that allowed end-users to see why predictions were made, and then to change weights on features to "debug" fairness issues. We evaluated the use of this prototype system through an online study. To investigate the implications of diverse human values about fairness around the globe, we also explored how cultural dimensions might play a role in using this prototype. Our results contribute to the design of interfaces to allow end-users to be involved in judging and addressing AI fairness through a human-in-the-loop approach.

Concept Embedding Analysis: A Review

Gesina Schwalbe

Deep neural networks (DNNs) have found their way into many applications with potential impact on the safety, security, and fairness of human-machine-systems. Such require basic understanding and sufficient trust by the users. This motivated the research field of explainable artificial intelligence (XAI), i.e. finding methods for opening the "black-boxes" DNNs represent. For the computer vision domain in specific, practical assessment of DNNs requires a globally valid association of human interpretable concepts with internals of the model. The research field of concept (embedding) analysis (CA) tackles this problem: CA aims to find global, assessable associations of humanly interpretable semantic concepts (e.g., eye, bearded) with internal representations of a DNN. This work establishes a general definition of CA and a taxonomy for CA methods, uniting several ideas from literature. That allows to easily position and compare CA approaches. Guided by the defined notions, the current state-of-the-art research regarding CA methods and interesting applications are reviewed. More than thirty relevant methods are discussed, compared, and categorized. Finally, for practitioners, a survey of fifteen datasets is provided that have been used for supervised concept analysis. Open challenges and research directions are pointed out at the end.

Explanation methods and their evaluation have become a significant issue in explainable artificial intelligence (XAI) due to the recent surge of opaque AI models in decision support systems (DSS). Since the most accurate AI models are opaque with low transparency and comprehensibility, explanations are essential for bias detection and control of uncertainty. There are a plethora of criteria to choose from when evaluating explanation method quality. However, since existing criteria focus on evaluating single explanation methods, it is not obvious how to compare the quality of different methods. This lack of consensus creates a critical shortage of rigour in the field, although little is written about comparative evaluations of explanation methods. In this paper, we have conducted a semi-systematic meta-survey over fifteen literature surveys covering the evaluation of explainability to identify existing criteria usable for comparative evaluations of explanation methods. The main contribution in the paper is the suggestion to use appropriate trust as a criterion to measure the outcome of the subjective evaluation criteria and consequently make comparative evaluations possible. We also present a model of explanation quality aspects. In the model, criteria with similar definitions are grouped and related to three identified aspects of quality; model, explanation, and user. We also notice four commonly accepted criteria (groups) in the literature, covering all aspects of explanation quality: Performance, appropriate trust, explanation satisfaction, and fidelity. We suggest the model be used as a chart for comparative evaluations to create more generalisable research in explanation quality.