Research Papers

The increasing development in the consumer credit card market brings substantial regulatory and risk management challenges. The advanced machine learning models applications bring concerns about model transparency and fairness for both financial institutions and regulatory departments. In this study, we evaluate the consistency of one commonly used Explainable AI (XAI) technology, SHAP, for variable explanation in credit card probability of default models via a case study about credit card default prediction. The study shows the consistency is related to the variable importance level and hence provides practical recommendation for credit risk management

The Singapore Consensus on Global AI Safety Research Priorities

Yoshua Bengio, Tegan Maharaj, Luke Ong +85

Rapidly improving AI capabilities and autonomy hold significant promise of transformation, but are also driving vigorous debate on how to ensure that AI is safe, i.e., trustworthy, reliable, and secure. Building a trusted ecosystem is therefore essential -- it helps people embrace AI with confidence and gives maximal space for innovation while avoiding backlash. The "2025 Singapore Conference on AI (SCAI): International Scientific Exchange on AI Safety" aimed to support research in this space by bringing together AI scientists across geographies to identify and synthesise research priorities in AI safety. This resulting report builds on the International AI Safety Report chaired by Yoshua Bengio and backed by 33 governments. By adopting a defence-in-depth model, this report organises AI safety research domains into three types: challenges with creating trustworthy AI systems (Development), challenges with evaluating their risks (Assessment), and challenges with monitoring and intervening after deployment (Control).

Artificial Intelligence (AI) governance is the practice of establishing frameworks, policies, and procedures to ensure the responsible, ethical, and safe development and deployment of AI systems. Although AI governance is a core pillar of Responsible AI, current literature still lacks synthesis across such governance frameworks and practices. Objective: To identify which frameworks, principles, mechanisms, and stakeholder roles are emphasized in secondary literature on AI governance. Method: We conducted a rapid tertiary review of nine peer-reviewed secondary studies from IEEE and ACM (20202024), using structured inclusion criteria and thematic semantic synthesis. Results: The most cited frameworks include the EU AI Act and NIST RMF; transparency and accountability are the most common principles. Few reviews detail actionable governance mechanisms or stakeholder strategies. Conclusion: The review consolidates key directions in AI governance and highlights gaps in empirical validation and inclusivity. Findings inform both academic inquiry and practical adoption in organizations.

This paper introduces LoBOX (Lack of Belief: Opacity \& eXplainability) governance ethic structured framework for managing artificial intelligence (AI) opacity when full transparency is infeasible. Rather than treating opacity as a design flaw, LoBOX defines it as a condition that can be ethically governed through role-calibrated explanation and institutional accountability. The framework comprises a three-stage pathway: reduce accidental opacity, bound irreducible opacity, and delegate trust through structured oversight. Integrating the RED/BLUE XAI model for stakeholder-sensitive explanation and aligned with emerging legal instruments such as the EU AI Act, LoBOX offers a scalable and context-aware alternative to transparency-centric approaches. Reframe trust not as a function of complete system explainability, but as an outcome of institutional credibility, structured justification, and stakeholder-responsive accountability. A governance loop cycles back to ensure that LoBOX remains responsive to evolving technological contexts and stakeholder expectations, to ensure the complete opacity governance. We move from transparency ideals to ethical governance, emphasizing that trustworthiness in AI must be institutionally grounded and contextually justified. We also discuss how cultural or institutional trust varies in different contexts. This theoretical framework positions opacity not as a flaw but as a feature that must be actively governed to ensure responsible AI systems.

Multi-agent autonomous systems (MAS) are better at addressing challenges that spans across multiple domains than singular autonomous agents. This holds true within the field of software engineering (SE) as well. The state-of-the-art research on MAS within SE focuses on integrating LLMs at the core of autonomous agents to create LLM-based multi-agent autonomous (LMA) systems. However, the introduction of LMA systems into SE brings a plethora of challenges. One of the major challenges is the strategic allocation of tasks between humans and the LMA system in a trustworthy manner. To address this challenge, a RACI-based framework is proposed in this work in progress article, along with implementation guidelines and an example implementation of the framework. The proposed framework can facilitate efficient collaboration, ensure accountability, and mitigate potential risks associated with LLM-driven automation while aligning with the Trustworthy AI guidelines. The future steps for this work delineating the planned empirical validation method are also presented.

AI Safety Assurance for Automated Vehicles: A Survey on Research, Standardization, Regulation

Lars Ullrich, Michael Buchholz, Klaus Dietmayer +1

Assuring safety of artificial intelligence (AI) applied to safety-critical systems is of paramount importance. Especially since research in the field of automated driving shows that AI is able to outperform classical approaches, to handle higher complexities, and to reach new levels of autonomy. At the same time, the safety assurance required for the use of AI in such safety-critical systems is still not in place. Due to the dynamic and far-reaching nature of the technology, research on safeguarding AI is being conducted in parallel to AI standardization and regulation. The parallel progress necessitates simultaneous consideration in order to carry out targeted research and development of AI systems in the context of automated driving. Therefore, in contrast to existing surveys that focus primarily on research aspects, this paper considers research, standardization and regulation in a concise way. Accordingly, the survey takes into account the interdependencies arising from the triplet of research, standardization and regulation in a forward-looking perspective and anticipates and discusses open questions and possible future directions. In this way, the survey ultimately serves to provide researchers and safety experts with a compact, holistic perspective that discusses the current status, emerging trends, and possible future developments.

The way we work is no longer hybrid -- it is blended with AI co-workers, automated decisions, and virtual presence reshaping human roles, agency, and expertise. We now work through AI, with our outputs shaped by invisible algorithms. AI's infiltration into knowledge, creative, and service work is not just about automation, but concerns redistribution of agency, creativity, and control. How do we deal with physical and distributed AI-mediated workspaces? What happens when algorithms co-author reports, and draft our creative work? In this provocation, we argue that hybrid work is obsolete. Blended work is the future, not just in physical and virtual spaces but in how human effort and AI output become inseparable. We argue this shift demands urgent attention to AI-mediated work practices, work-life boundaries, physical-digital interactions, and AI transparency and accountability. The question is not whether we accept it, but whether we actively shape it before it shapes us.

Understanding how information is represented in neural networks is a fundamental challenge in both neuroscience and artificial intelligence. Despite their nonlinear architectures, recent evidence suggests that neural networks encode features in superposition, meaning that input concepts are linearly overlaid within the network's representations. We present a perspective that explains this phenomenon and provides a foundation for extracting interpretable representations from neural activations. Our theoretical framework consists of three steps: (1) Identifiability theory shows that neural networks trained for classification recover latent features up to a linear transformation. (2) Sparse coding methods can extract disentangled features from these representations by leveraging principles from compressed sensing. (3) Quantitative interpretability metrics provide a means to assess the success of these methods, ensuring that extracted features align with human-interpretable concepts. By bridging insights from theoretical neuroscience, representation learning, and interpretability research, we propose an emerging perspective on understanding neural representations in both artificial and biological systems. Our arguments have implications for neural coding theories, AI transparency, and the broader goal of making deep learning models more interpretable.

Explingo: Explaining AI Predictions using Large Language Models

Alexandra Zytek, Sara Pido, Sarah Alnegheimish +2

Explanations of machine learning (ML) model predictions generated by Explainable AI (XAI) techniques such as SHAP are essential for people using ML outputs for decision-making. We explore the potential of Large Language Models (LLMs) to transform these explanations into human-readable, narrative formats that align with natural communication. We address two key research questions: (1) Can LLMs reliably transform traditional explanations into high-quality narratives? and (2) How can we effectively evaluate the quality of narrative explanations? To answer these questions, we introduce Explingo, which consists of two LLM-based subsystems, a Narrator and Grader. The Narrator takes in ML explanations and transforms them into natural-language descriptions. The Grader scores these narratives on a set of metrics including accuracy, completeness, fluency, and conciseness. Our experiments demonstrate that LLMs can generate high-quality narratives that achieve high scores across all metrics, particularly when guided by a small number of human-labeled and bootstrapped examples. We also identified areas that remain challenging, in particular for effectively scoring narratives in complex domains. The findings from this work have been integrated into an open-source tool that makes narrative explanations available for further applications.

The goal of the present study is to analyze an application of deep learning models in order to augment the diagnostic performance of oral squamous cell carcinoma (OSCC) with a longitudinal cohort study using the Histopathological Imaging Database for oral cancer analysis. The dataset consisted of 5192 images (2435 Normal and 2511 OSCC), which were allocated between training, testing, and validation sets with an estimated ratio repartition of about 52% for the OSCC group, and still, our performance measure was validated on a combination set that contains almost equal number of sample in this use case as entire database have been divided into half using stratified splitting technique based again near binary proportion but total distribution was around even. We selected four deep-learning architectures for evaluation in the present study: ResNet101, DenseNet121, VGG16, and EfficientnetB3. EfficientNetB3 was found to be the best, with an accuracy of 98.33% and F1 score (0.9844), and it took remarkably less computing power in comparison with other models. The subsequent one was DenseNet121, with 90.24% accuracy and an F1 score of 90.45%. Moreover, we employed the Local Interpretable Model-agnostic Explanations (LIME) method to clarify why EfficientNetB3 made certain decisions with its predictions to improve the explainability and trustworthiness of results. This work provides evidence for the possible superior diagnosis in OSCC activated from the EfficientNetB3 model with the explanation of AI techniques such as LIME and paves an important groundwork to build on towards clinical usage.

Large language models (LLMs) are increasingly shaping citizens' information ecosystems. Products incorporating LLMs, such as chatbots and AI Companions, are now widely used for decision support and information retrieval, including in sensitive domains, raising concerns about hidden biases and growing potential to shape individual decisions and public opinion. This paper introduces GermanPartiesQA, a benchmark of 418 political statements from German Voting Advice Applications across 11 elections to evaluate six commercial LLMs. We evaluate their political alignment based on role-playing experiments with political personas. Our evaluation reveals three specific findings: (1) Factual limitations: LLMs show limited ability to accurately generate factual party positions, particularly for centrist parties. (2) Model-specific ideological alignment: We identify consistent alignment patterns and the degree of political steerability for each model across temperature settings and experiments. (3) Claim of sycophancy: While models adjust to political personas during role-play, we find this reflects persona-based steerability rather than the increasingly popular, yet contested concept of sycophancy. Our study contributes to evaluating the political alignment of closed-source LLMs that are increasingly embedded in electoral decision support tools and AI Companion chatbots.

As an AI Language Model, "Yes I Would Recommend Calling the Police": Norm Inconsistency in LLM Decision-Making

Shomik Jain, D Calacci, Ashia Wilson

We investigate the phenomenon of norm inconsistency: where LLMs apply different norms in similar situations. Specifically, we focus on the high-risk application of deciding whether to call the police in Amazon Ring home surveillance videos. We evaluate the decisions of three state-of-the-art LLMs -- GPT-4, Gemini 1.0, and Claude 3 Sonnet -- in relation to the activities portrayed in the videos, the subjects' skin-tone and gender, and the characteristics of the neighborhoods where the videos were recorded. Our analysis reveals significant norm inconsistencies: (1) a discordance between the recommendation to call the police and the actual presence of criminal activity, and (2) biases influenced by the racial demographics of the neighborhoods. These results highlight the arbitrariness of model decisions in the surveillance context and the limitations of current bias detection and mitigation strategies in normative decision-making.