Research Papers

Deep learning models in medical imaging often achieve strong in-distribution performance but struggle to generalise under distribution shifts, frequently relying on spurious correlations instead of clinically meaningful features. We introduce LCRReg, a novel regularisation approach that leverages Latent Concept Representations (LCRs) (e.g., Concept Activation Vectors (CAVs)) to guide models toward semantically grounded representations. LCRReg requires no concept labels in the main training set and instead uses a small auxiliary dataset to synthesise high-quality, disentangled concept examples. We extract LCRs for predefined relevant features, and incorporate a regularisation term that guides a Convolutional Neural Network (CNN) to activate within latent subspaces associated with those concepts. We evaluate LCRReg across synthetic and real-world medical tasks. On a controlled toy dataset, it significantly improves robustness to injected spurious correlations and remains effective even in multi-concept and multiclass settings. On the diabetic retinopathy binary classification task, LCRReg enhances performance under both synthetic spurious perturbations and out-of-distribution (OOD) generalisation. Compared to baselines, including multitask learning, linear probing, and post-hoc concept-based models, LCRReg offers a lightweight, architecture-agnostic strategy for improving model robustness without requiring dense concept supervision. Code is available at the following link: https://github.com/Trustworthy-AI-UU-NKI/lcr\_regularization

The clinical deployment of deep learning models for high-stakes tasks such as diabetic retinopathy (DR) grading requires demonstrable reliability. While models achieve high accuracy, their clinical utility is limited by a lack of robust uncertainty quantification. Conformal prediction (CP) offers a distribution-free framework to generate prediction sets with statistical guarantees of coverage. However, the interaction between standard training practices like data augmentation and the validity of these guarantees is not well understood. In this study, we systematically investigate how different data augmentation strategies affect the performance of conformal predictors for DR grading. Using the DDR dataset, we evaluate two backbone architectures -- ResNet-50 and a Co-Scale Conv-Attentional Transformer (CoaT) -- trained under five augmentation regimes: no augmentation, standard geometric transforms, CLAHE, Mixup, and CutMix. We analyze the downstream effects on conformal metrics, including empirical coverage, average prediction set size, and correct efficiency. Our results demonstrate that sample-mixing strategies like Mixup and CutMix not only improve predictive accuracy but also yield more reliable and efficient uncertainty estimates. Conversely, methods like CLAHE can negatively impact model certainty. These findings highlight the need to co-design augmentation strategies with downstream uncertainty quantification in mind to build genuinely trustworthy AI systems for medical imaging.

This review synthesizes the nascent but critical field of developmental interpretability for Large Language Models. We chart the field's evolution from static, post-hoc analysis of trained models to a dynamic investigation of the training process itself. We begin by surveying the foundational methodologies, including representational probing, causal tracing, and circuit analysis, that enable researchers to deconstruct the learning process. The core of this review examines the developmental arc of LLM capabilities, detailing key findings on the formation and composition of computational circuits, the biphasic nature of knowledge acquisition, the transient dynamics of learning strategies like in-context learning, and the phenomenon of emergent abilities as phase transitions in training. We explore illuminating parallels with human cognitive and linguistic development, which provide valuable conceptual frameworks for understanding LLM learning. Finally, we argue that this developmental perspective is not merely an academic exercise but a cornerstone of proactive AI safety, offering a pathway to predict, monitor, and align the processes by which models acquire their capabilities. We conclude by outlining the grand challenges facing the field, such as scalability and automation, and propose a research agenda for building more transparent, reliable, and beneficial AI systems.

Deep learning models are one of the security strategies, trained on extensive datasets, and play a critical role in detecting and responding to these threats by recognizing complex patterns in malicious code. However, the opaque nature of these models-often described as "black boxes"-makes their decision-making processes difficult to understand, even for their creators. This research addresses these challenges by integrating Explainable AI (XAI) techniques to enhance the interpretability and trustworthiness of malware detection models. In this research, the use of Multi-Layer Perceptrons (MLP) for dynamic malware analysis has been considered, a less explored area, and its efficacy in detecting Metamorphic Malware, and further the effectiveness and transparency of MLPs, CNNs, RNNs, and CNN-LSTM models in malware classification, evaluating these models through the lens of Explainable AI (XAI). This comprehensive approach aims to demystify the internal workings of deep learning models, promoting a better understanding and trust in their predictive capabilities in cybersecurity contexts. Such in-depth analysis and implementation haven't been done to the best of our knowledge.

As AI systems are increasingly deployed to support decision-making in critical domains, explainability has become a means to enhance the understandability of these outputs and enable users to make more informed and conscious choices. However, despite growing interest in the usability of eXplainable AI (XAI), the accessibility of these methods, particularly for users with vision impairments, remains underexplored. This paper investigates accessibility gaps in XAI through a two-pronged approach. First, a literature review of 79 studies reveals that evaluations of XAI techniques rarely include disabled users, with most explanations relying on inherently visual formats. Second, we present a four-part methodological proof of concept that operationalizes inclusive XAI design: (1) categorization of AI systems, (2) persona definition and contextualization, (3) prototype design and implementation, and (4) expert and user assessment of XAI techniques for accessibility. Preliminary findings suggest that simplified explanations are more comprehensible for non-visual users than detailed ones, and that multimodal presentation is required for more equitable interpretability.

The attention mechanism lies at the core of the transformer architecture, providing an interpretable model-internal signal that has motivated a growing interest in attention-based model explanations. Although attention weights do not directly determine model outputs, they reflect patterns of token influence that can inform and complement established explainability techniques. This work studies the potential of utilising the information encoded in attention weights to provide meaningful model explanations by integrating them into explainable AI (XAI) frameworks that target fundamentally different aspects of model behaviour. To this end, we develop two novel explanation methods applicable to both natural language processing and computer vision tasks. The first integrates attention weights into the Shapley value decomposition by redefining the characteristic function in terms of pairwise token interactions via attention weights, thus adapting this widely used game-theoretic solution concept to provide attention-driven attributions for local explanations. The second incorporates attention weights into token-level directional derivatives defined through concept activation vectors to measure concept sensitivity for global explanations. Our empirical evaluations on standard benchmarks and in a comparison study with widely used explanation methods show that attention weights can be meaningfully incorporated into the studied XAI frameworks, highlighting their value in enriching transformer explainability.

The field of Explainable AI (XAI) offers a wide range of techniques for making complex models interpretable. Yet, in practice, generating meaningful explanations is a context-dependent task that requires intentional design choices to ensure accessibility and transparency. This paper reframes explanation as a situated design process -- an approach particularly relevant for practitioners involved in building and deploying explainable systems. Drawing on prior research and principles from design thinking, we propose a three-part framework for explanation design in XAI: asking Who needs the explanation, What they need explained, and How that explanation should be delivered. We also emphasize the need for ethical considerations, including risks of epistemic inequality, reinforcing social inequities, and obscuring accountability and governance. By treating explanation as a sociotechnical design process, this framework encourages a context-aware approach to XAI that supports effective communication and the development of ethically responsible explanations.

Highlight All the Phrases: Enhancing LLM Transparency through Visual Factuality Indicators

Hyo Jin Do, Rachel Ostrand, Werner Geyer +3

Large language models (LLMs) are susceptible to generating inaccurate or false information, often referred to as "hallucinations" or "confabulations." While several technical advancements have been made to detect hallucinated content by assessing the factuality of the model's responses, there is still limited research on how to effectively communicate this information to users. To address this gap, we conducted two scenario-based experiments with a total of 208 participants to systematically compare the effects of various design strategies for communicating factuality scores by assessing participants' ratings of trust, ease in validating response accuracy, and preference. Our findings reveal that participants preferred and trusted a design in which all phrases within a response were color-coded based on factuality scores. Participants also found it easier to validate accuracy of the response in this style compared to a baseline with no style applied. Our study offers practical design guidelines for LLM application developers and designers, aimed at calibrating user trust, aligning with user preferences, and enhancing users' ability to scrutinize LLM outputs.

We explore machine learning techniques for predicting Curie temperatures of magnetic materials using the NEMAD database. By augmenting the dataset with composition-based and domain-aware descriptors, we evaluate the performance of several machine learning models. We find that the Extra Trees Regressor delivers the best performance reaching an R^2 score of up to 0.85 $\pm$ 0.01 (cross-validated) for a balanced dataset. We employ the k-means clustering algorithm to gain insights into the performance of chemically distinct material groups. Furthermore, we perform the SHAP analysis to identify key physicochemical drivers of Curie behavior, such as average atomic number and magnetic moment. By employing explainable AI techniques, this analysis offers insights into the model's predictive behavior, thereby advancing scientific interpretability.

As AI systems become increasingly embedded in organizational workflows and consumer applications, ethical principles such as fairness, transparency, and robustness have been widely endorsed in policy and industry guidelines. However, there is still scarce empirical evidence on whether these principles are recognized, valued, or impactful from the perspective of users. This study investigates the link between ethical AI and user satisfaction by analyzing over 100,000 user reviews of AI products from G2. Using transformer-based language models, we measure sentiment across seven ethical dimensions defined by the EU Ethics Guidelines for Trustworthy AI. Our findings show that all seven dimensions are positively associated with user satisfaction. Yet, this relationship varies systematically across user and product types. Technical users and reviewers of AI development platforms more frequently discuss system-level concerns (e.g., transparency, data governance), while non-technical users and reviewers of end-user applications emphasize human-centric dimensions (e.g., human agency, societal well-being). Moreover, the association between ethical AI and user satisfaction is significantly stronger for non-technical users and end-user applications across all dimensions. Our results highlight the importance of ethical AI design from users' perspectives and underscore the need to account for contextual differences across user roles and product types.

Demystifying Sequential Recommendations: Counterfactual Explanations via Genetic Algorithms

Domiziano Scarcelli, Filippo Betello, Giuseppe Perelli +2

Sequential Recommender Systems (SRSs) have demonstrated remarkable effectiveness in capturing users' evolving preferences. However, their inherent complexity as "black box" models poses significant challenges for explainability. This work presents the first counterfactual explanation technique specifically developed for SRSs, introducing a novel approach in this space, addressing the key question: What minimal changes in a user's interaction history would lead to different recommendations? To achieve this, we introduce a specialized genetic algorithm tailored for discrete sequences and show that generating counterfactual explanations for sequential data is an NP-Complete problem. We evaluate these approaches across four experimental settings, varying between targeted-untargeted and categorized-uncategorized scenarios, to comprehensively assess their capability in generating meaningful explanations. Using three different datasets and three models, we are able to demonstrate that our methods successfully generate interpretable counterfactual explanation while maintaining model fidelity close to one. Our findings contribute to the growing field of Explainable AI by providing a framework for understanding sequential recommendation decisions through the lens of "what-if" scenarios, ultimately enhancing user trust and system transparency.

Large language models (LLMs) are increasingly deployed in sensitive contexts where fairness and inclusivity are critical. Pronoun usage, especially concerning gender-neutral and neopronouns, remains a key challenge for responsible AI. Prior work, such as the MISGENDERED benchmark, revealed significant limitations in earlier LLMs' handling of inclusive pronouns, but was constrained to outdated models and limited evaluations. In this study, we introduce MISGENDERED+, an extended and updated benchmark for evaluating LLMs' pronoun fidelity. We benchmark five representative LLMs, GPT-4o, Claude 4, DeepSeek-V3, Qwen Turbo, and Qwen2.5, across zero-shot, few-shot, and gender identity inference. Our results show notable improvements compared with previous studies, especially in binary and gender-neutral pronoun accuracy. However, accuracy on neopronouns and reverse inference tasks remains inconsistent, underscoring persistent gaps in identity-sensitive reasoning. We discuss implications, model-specific observations, and avenues for future inclusive AI research.