Research Papers

Explainable Artificial Intelligence (XAI) is a rising field in AI. It aims to produce a demonstrative factor of trust, which for human subjects is achieved through communicative means, which Machine Learning (ML) algorithms cannot solely produce, illustrating the necessity of an extra layer producing support to the model output. When approaching the medical field, we can see challenges arise when dealing with the involvement of human-subjects, the ideology behind trusting a machine to tend towards the livelihood of a human poses an ethical conundrum - leaving trust as the basis of the human-expert in acceptance to the machines decision. The aim of this paper is to apply XAI methods to demonstrate the usability of explainable architectures as a tertiary layer for the medical domain supporting ML predictions and human-expert opinion, XAI methods produce visualization of the feature contribution towards a given models output on both a local and global level. The work in this paper uses XAI to determine feature importance towards high-dimensional data-driven questions to inform domain-experts of identifiable trends with a comparison of model-agnostic methods in application to ML algorithms. The performance metrics for a glass-box method is also provided as a comparison against black-box capability for tabular data. Future work will aim to produce a user-study using metrics to evaluate human-expert usability and opinion of the given models.

Proof-Carrying Plans: a Resource Logic for AI Planning

Alasdair Hill, Ekaterina Komendantskaya, Ronald P. A. Petrick

Recent trends in AI verification and Explainable AI have raised the question of whether AI planning techniques can be verified. In this paper, we present a novel resource logic, the Proof Carrying Plans (PCP) logic that can be used to verify plans produced by AI planners. The PCP logic takes inspiration from existing resource logics (such as Linear logic and Separation logic) as well as Hoare logic when it comes to modelling states and resource-aware plan execution. It also capitalises on the Curry-Howard approach to logics, in its treatment of plans as functions and plan pre- and post-conditions as types. This paper presents two main results. From the theoretical perspective, we show that the PCP logic is sound relative to the standard possible world semantics used in AI planning. From the practical perspective, we present a complete Agda formalisation of the PCP logic and of its soundness proof. Moreover, we showcase the Curry-Howard, or functional, value of this implementation by supplementing it with the library that parses AI plans into Agda's proofs automatically. We provide evaluation of this library and the resulting Agda functions.

In recent years, curial incidents and accidents have been reported due to un-intended control caused by misjudgment of statistical machine learning (SML), which include deep learning. The international functional safety standards for Electric/Electronic/Programmable (E/E/P) systems have been widely spread to improve safety. However, most of them do not recom-mended to use SML in safety critical systems so far. In practical the new concepts and methods are urgently required to enable SML to be safely used in safety critical systems. In this paper, we organize five kinds of technical safety concepts (TSCs) for SML components toward accordance with functional safety standards. We discuss not only quantitative evaluation criteria, but also development process based on XAI (eXplainable Artificial Intelligence) and Automotive SPICE to improve explainability and reliability in development phase. Fi-nally, we briefly compare the TSCs in cost and difficulty, and expect to en-courage further discussion in many communities and domain.

The car-to-driver handover is a critically important component of safe autonomous vehicle operation when the vehicle is unable to safely proceed on its own. Current implementations of this handover in automobiles take the form of a generic alarm indicating an imminent transfer of control back to the human driver. However, certain levels of vehicle autonomy may allow the driver to engage in other, non-driving related tasks prior to a handover, leading to substantial difficulty in quickly regaining situational awareness. This delay in re-orientation could potentially lead to life-threatening failures unless mitigating steps are taken. Explainable AI has been shown to improve fluency and teamwork in human-robot collaboration scenarios. Therefore, we hypothesize that by utilizing autonomous explanation, these car-to-driver handovers can be performed more safely and reliably. The rationale is, by providing the driver with additional situational knowledge, they will more rapidly focus on the relevant parts of the driving environment. Towards this end, we propose an algorithmic failure-mode identification and explanation approach to enable informed handovers from vehicle to driver. Furthermore, we propose a set of human-subjects driving-simulator studies to determine the appropriate form of explanation during handovers, as well as validate our framework.

Induction of Non-Monotonic Rules From Statistical Learning Models Using High-Utility Itemset Mining

Farhad Shakerin, Gopal Gupta

We present a fast and scalable algorithm to induce non-monotonic logic programs from statistical learning models. We reduce the problem of search for best clauses to instances of the High-Utility Itemset Mining (HUIM) problem. In the HUIM problem, feature values and their importance are treated as transactions and utilities respectively. We make use of TreeExplainer, a fast and scalable implementation of the Explainable AI tool SHAP, to extract locally important features and their weights from ensemble tree models. Our experiments with UCI standard benchmarks suggest a significant improvement in terms of classification evaluation metrics and running time of the training algorithm compared to ALEPH, a state-of-the-art Inductive Logic Programming (ILP) system.

This paper describes a design that can be used for Explainable AI. The lower level is a nested ensemble of patterns created by self-organisation. The upper level is a hierarchical tree, where nodes are linked through individual concepts, so there is a transition from mixed ensemble masses to specific categories. Lower-level pattern ensembles are learned in an unsupervsised manner and then split into branches when it is clear that the category has changed. Links between the two levels define that the concepts are learned and missing links define that they are guessed only. This paper proposes some new clustering algorithms for producing the pattern ensembles, that are themselves an ensemble which converges through aggregations. Multiple solutions are also combined, to make the final result more robust. One measure of success is how coherent these ensembles are, which means that every data row in the cluster belongs to the same category. The total number of clusters is also important and the teaching phase can correct the ensemble estimates with respect to both of these. A teaching phase would then help the classifier to learn the true category for each input row. During this phase, any classifier can learn or infer correct classifications from some other classifier's knowledge, thereby reducing the required number of presentations. As the information is added, cross-referencing between the two structures allows it to be used more widely, where a unique structure can build up that would not be possible by either method separately.

Neuron-Anchored Rule Extraction for Large Language Models via Contrastive Hierarchical Ablation

Francesco Sovrano, Gabriele Dominici, Marc Langheinrich

A central goal of explainable AI is to express large language model (LLM) decision logic symbolically and ground it in internal mechanisms. Existing rule-extraction methods usually learn ungrounded symbolic surrogates, while mechanistic interpretability links behavior to neurons but often requires hand-crafted hypotheses and costly interventions. We introduce MechaRule, a pipeline that grounds rule extraction in LLM circuits by localizing sparse agonist activations whose ablation disrupts rule-related behavior. MechaRule rests on two findings. First, in a fixed baseline/flip regime, sparse agonist effects can exhibit overtopping: a few high-effect activations remain detectable within larger groups, dominate weaker ones, and flip many of the same examples. In such regimes, adaptive group testing with confidence-guided conservative pruning requires O(k log(N/k) + k) interventions over N candidates when k << N are agonists. Second, agonists are localized more reliably on data splits aligned with close-to-faithful rule behavior; spectral splits provide a rule-free fallback, whereas unfaithful splits degrade localization. Empirically, on arithmetic and jailbreaking, MechaRule recalls 97.0% of highest-effect agonists in matched brute-force validations at only 2.14% of exhaustive-ablation cost on average. Ablating the localized agonists eliminates 97.6--100.0% of eligible correct arithmetic answers and jailbreaks, and can correct arithmetic errors or induce jailbreaks by up to 72.8% and 32.5%.

Neural networks can be trained to learn task-relevant representations from data. Understanding how these networks make decisions falls within the Explainable AI (XAI) domain. This paper proposes to study an XAI topic: analysing, visualising and understanding the unknown organisation of network representations, particularly those a speaker recognition network learns from utterances, for recognising speaker identity. Past studies have employed algorithms (e.g. K-means) to analyse the different ways in which network representations can be naturally grouped into clusters, i.e. to analyse different flat clustering phenomena within the space defined by those representations. In contrast, this work applies two algorithms -- Single-Linkage Clustering (SLINK) and Hierarchical Density-Based Spatial Clustering of Applications with Noise (HDBSCAN) -- to analyse the different ways in which representations from the speaker recognition network can form clusters with hierarchical relationships, i.e., to analyse different hierarchical clustering phenomena within the representation space of the speaker recognition network. Furthermore, an algorithm called Hierarchical Cluster-Class Matching (HCCM) is designed to semantically interpret one of the above hierarchical clustering phenomena analysed using SLINK. Given the clusters representing this phenomenon, HCCM identifies which ones best match individual semantic classes related to gender and nationality (e.g.\ male, female, Ireland, UK) and and-logic conjunctions of these classes (e.g.\ female and Ireland). The Liebig score metric is also proposed within HCCM to quantify the matching quality of each cluster-class pair and diagnose the factor that limits each match.

Interpretable and Explainable Surrogate Modeling for Simulations: A State-of-the-Art Survey and Perspectives on Explainable AI for Decision-Making

Pramudita Satria Palar, Paul Saves, Muhammad Daffa Robani +6

The simulation of complex systems increasingly relies on sophisticated but fundamentally opaque computational black-box simulators. Surrogate models play a central role in reducing the computational cost of complex systems simulations across a wide range of scientific and engineering domains. Notwithstanding, they inevitably inherit and often exacerbate this black-box nature, obscuring how input variables drive physical responses. Conversely, Explainable Artificial Intelligence (XAI) offers powerful tools to unpack these models. Yet, XAI methods struggle with engineering-specific constraints, such as highly correlated inputs, dynamical systems, and rigorous reliability requirements. Consequently, surrogate modeling and XAI have largely evolved as distinct fields of research, despite their strong complementarity. To reconnect these approaches, this state-of-the-art survey provides a structured perspective that maps existing XAI techniques onto the various stages of surrogate modeling workflows for design and exploration. To ground this synthesis, we draw upon illustrative applications across both equation-based simulations and agent-based modeling. We survey a broad spectrum of techniques, highlighting their strengths for revealing interactions and supporting human comprehension. Finally, we identify pressing open challenges, including the explainability of dynamical systems and the handling of mixed-variable systems, and propose a research agenda to make explainability a core, embedded element of simulation-driven workflows from model construction through decision-making. By transforming opaque emulators into explainable tools, this agenda empowers practitioners to move beyond accelerating simulations to extracting actionable insights from complex system behaviors.

Modern agentic workflows decompose complex tasks into specialized subtasks and route them to diverse models to minimize cost without sacrificing quality. However, current routing architectures focus exclusively on performance optimization, leaving underlying trade-offs between model capability and cost unrecorded. Without clear rationale, developers cannot distinguish between intelligent efficiency -- using specialized models for appropriate tasks -- and latent failures caused by budget-driven model selection. We present Topaz, a framework that introduces formal auditability to agentic routing. Topaz replaces silent model assignments with an inherently interpretable router that incorporates three components: (i) skill-based profiling that synthesizes performance across diverse benchmarks into granular capability profiles (ii) fully traceable routing algorithms that utilize budget-based and multi-objective optimization to produce clear traces of how skill-match scores were weighed against costs, and (iii) developer-facing explanations that translate these traces into natural language, allowing users to audit system logic and iteratively tune the cost-quality tradeoff. By making routing decisions interpretable, Topaz enables users to understand, trust, and meaningfully steer routed agentic systems.

Explainable AI for Blind and Low-Vision Users: Navigating Trust, Modality, and Interpretability in the Agentic Era

Abu Noman Md Sakib, Protik Dey, Zijie Zhang +1

Explainable Artificial Intelligence (XAI) is critical for ensuring trust and accountability, yet its development remains predominantly visual. For blind and low-vision (BLV) users, the lack of accessible explanations creates a fundamental barrier to the independent use of AI-driven assistive technologies. This problem intensifies as AI systems shift from single-query tools into autonomous agents that take multi-step actions and make consequential decisions across extended task horizons, where a single undetected error can propagate irreversibly before any feedback is available. This paper investigates the unique XAI requirements of the BLV community through a comprehensive analysis of user interviews and contemporary research. By examining usage patterns across environmental perception and decision support, we identify a significant modality gap. Empirical evidence suggests that while BLV users highly value conversational explanations, they frequently experience "self-blame" for AI failures. The paper concludes with a research agenda for accessible Explainable AI in agentic systems, advocating for multimodal interfaces, blame-aware explanation design, and participatory development.

The widespread adoption of Large Language Models (LLMs) has made the detection of AI-Generated text a pressing and complex challenge. Although many detection systems report high benchmark accuracy, their reliability in real-world settings remains uncertain, and their interpretability is often unexplored. In this work, we investigate whether contemporary detectors genuinely identify machine authorship or merely exploit dataset-specific artefacts. We propose an interpretable detection framework that integrates linguistic feature engineering, machine learning, and explainable AI techniques. When evaluated on two prominent benchmark corpora, namely PAN CLEF 2025 and COLING 2025, our model trained on 30 linguistic features achieves leaderboard-competitive performance, attaining an F1 score of 0.9734. However, systematic cross-domain and cross-generator evaluation reveals substantial generalisation failure: classifiers that excel in-domain degrade significantly under distribution shift. Using SHAP- based explanations, we show that the most influential features differ markedly between datasets, indicating that detectors often rely on dataset-specific stylistic cues rather than stable signals of machine authorship. Further investigation with in-depth error analysis exposes a fundamental tension in linguistic-feature-based AI text detection: the features that are most discriminative on in-domain data are also the features most susceptible to domain shift, formatting variation, and text-length effects. We believe that this knowledge helps build AI detectors that are robust across different settings. To support replication and practical use, we release an open-source Python package that returns both predictions and instance-level explanations for individual texts.