Education providers face increasing challenges in complying with complex and evolving funding regulations. While large language models (LLMs) have the potential to support providers with this task, LLM responses are prone to hallucinations and may omit key information. Ontologies and knowledge graphs (KGs) can help mitigate these risks by formally representing regulatory knowledge in a structured format. We present NeuReg, a neuro-symbolic question-answer (QA) generation framework that combines the language processing capabilities of LLMs with structured knowledge extracted from funding regulations. We explore multiple prompting techniques, generating 3,314 open-ended QA pairs consisting of factual, relational, comparative, and inferential questions. We compare the quality of QA pairs generated using different prompting strategies using both expert human reviewers and five LLM judges. The utility of the dataset is further demonstrated through a fine-tuned QA system trained on the NeuReg dataset. Our findings indicate that one-shot prompting offers an effective balance of quality and efficiency. All resources are at: github.com/RGU-Computing/NeuReg.

Explainable AI (XAI) can greatly enhance user trust and satisfaction in AI-assisted decision-making processes. Recent findings suggest that a single explainer may not meet the diverse needs of multiple users in an AI system; indeed, even individual users may require multiple explanations. This highlights the necessity for a “multi-shot” approach, employing a combination of explainers to form what we introduce as an “explanation strategy”. Tailored to a specific user or a user group, an “explanation experience” describes interactions with personalised strategies designed to enhance their AI decision-making processes. The iSee platform is designed for the intelligent sharing and reuse of explanation experiences, using Case-based Reasoning to advance best practices in XAI. The platform provides tools that enable AI system designers, i.e. design users, to design and iteratively revise the most suitable explanation strategy for their AI system to satisfy end-user needs. All knowledge generated within the iSee platform is formalised by the iSee ontology for interoperability. We use a summative mixed methods study protocol to evaluate the usability and utility of the iSEE platform with six design users across varying levels of AI and XAI expertise. Our findings confirm that the iSee platform effectively generalises across applications and its potential to promote the adoption of XAI best practices.

Explainable Artificial Intelligence (XAI) is an emerging field within Artificial Intelligence (AI) that has provided many methods that enable humans to understand and interpret the outcomes of AI systems. However, deciding on the best explanation approach for a given AI problem is currently a challenging decision-making task. This paper presents the iSee project, which aims to address some of the XAI challenges by providing a unifying platform where personalized explanation experiences are generated using Case-Based Reasoning. An explanation experience includes the proposed solution to a particular explainability problem and its corresponding evaluation, provided by the end user. The ultimate goal is to provide an open catalog of explanation experiences that can be transferred to other scenarios where trustworthy AI is required.

Counterfactual Explanations (cf-XAI) describe the smallest changes in feature values necessary to change an outcome from one class to another. However, many cf-XAI methods neglect the feasibility of those changes. In this paper, we introduce a novel approach for presenting cf-XAI in natural language (Natural-XAI), giving careful consideration to actionable and comprehensible aspects while remaining cognizant of immutability and ethical concerns. We present three contributions to this endeavor. Firstly, through a user study, we identify two types of themes present in cf-XAI composed by humans: content-related, focusing on how features and their values are included from both the counterfactual and the query perspectives; and structure-related, focusing on the structure and terminology used for describing necessary value changes. Secondly, we introduce a feature actionability taxonomy with four clearly defined categories, to streamline the explanation presentation process. Using insights from the user study and our taxonomy, we created a generalisable template-based natural language generation (NLG) method compatible with existing explainers like DICE, NICE, and DisCERN, to produce counterfactuals that address the aforementioned limitations of existing approaches. Finally, we conducted a second user study to assess the performance of our taxonomy-guided NLG templates on three domains. Our findings show that the taxonomy-guided Natural-XAI approach (n-XAIT) received higher user ratings across all dimensions, with significantly improved results in the majority of the domains assessed for articulation, acceptability, feasibility, and sensitivity dimensions.

Counterfactual explanations focus on "actionable knowledge" to help end-users understand how a machine learning outcome could be changed to a more desirable outcome. For this purpose a counterfactual explainer needs to discover input dependencies that relate to outcome changes. Identifying the minimum subset of feature changes needed to action an output change in the decision is an interesting challenge for counterfactual explainers. The DisCERN algorithm introduced in this paper is a case-based counter-factual explainer. Here counterfactuals are formed by replacing feature values from a nearest unlike neighbour (NUN) until an actionable change is observed. We show how widely adopted feature relevance-based explainers (i.e. LIME, SHAP), can inform DisCERN to identify the minimum subset of "actionable features". We demonstrate our DisCERN algorithm on five datasets in a comparative study with the widely used optimisation-based counterfactual approach DiCE. Our results demonstrate that DisCERN outperformed DiCE by minimising both the number of feature changes and the amount of change necessary to create good counterfactual explanations.

Recent technological advances in modern healthcare have lead to the ability to collect a vast wealth of patient monitoring data. This data can be utilised for patient diagnosis but it also holds the potential for use within medical research. However, these datasets often contain errors which limit their value to medical research, with one study finding error rates ranging from 2.3%-26.9% in a selection of medical databases. Previous methods for automatically assessing data quality normally rely on threshold rules, which are often unable to correctly identify errors, as further complex domain knowledge is required. To combat this, a semantic web based framework has previously been developed to assess the quality of medical data. However, early work, based solely on traditional semantic web technologies, revealed they are either unable or inefficient at scaling to the vast volumes of medical data. In this paper we present a new method for storing and querying medical RDF datasets using Hadoop Map / Reduce. This approach exploits the inherent parallelism found within RDF datasets and queries, allowing us to scale with both dataset and system size. Unlike previous solutions, this framework uses highly optimised (SPARQL) joining strategies, intelligent data caching and the use of a super-query to enable the completion of eight distinct SPARQL lookups, comprising over eighty distinct joins, in only two Map / Reduce iterations. Results are presented comparing both the Jena and a previous Hadoop implementation demonstrating the superior performance of the new methodology. The new method is shown to be five times faster than Jena and twice as fast as the previous approach.

Vast amounts of medical data are now routinely collected. This data is often subsequently used in medical research. However, the quality of the data can vary widely. Existing automated approaches to data quality assurance largely rely on threshold rules that can miss errors requiring complex domain knowledge to identify. In this paper we describe a framework to assess the reliability of medical data using linked data and semantic web technologies. This approach has been evaluated in the Neuro-Intensive Care Unit domain, successfully identifying potential errors in the recorded observations, and indicating that various ontologies proposed by the medical and sensor network communities can be used to represent medical observation data.

The benefits of Service Oriented Architectures for business are well recognised, however defining the correct composition of services for a particular business process can be very challenging. In this paper we present the ALIVE approach to composing Web services to meet business goals. Our approach involves the use of agents to enact plans of actions which achieve organisational goals, where each action specifies what should be achieved as opposed to which service to use. When enacting an action, agents use a matchmaking process to determine services that can be used to achieve the desired effects, intelligently handling any errors that may occur. The action plans are based on an organisation model, allowing the set of actions available to the plan synthesis mechanism to be tailored to the goal being targeted at that specific time, further reducing the planning search space.

The benefits of reuse have long been recognized in the knowledge engineering community where the dream of creating knowledge based systems (KBSs) on-the-fly from libraries of reusable components is still to be fully realised. In this paper we present a two stage methodology for creating KBSs: first reusing domain knowledge by mapping it, where appropriate, to the requirements of a generic problem solver; and secondly using this mapped knowledge and the requirements of the problem solver to "drive" the acquisition of the additional knowledge it needs.allFor example, suppose we have available a KBS which is composed of a propose-and-revise problem solver linked with an appropriate knowledge base/ontology from the elevator domain. Then to create a diagnostic KBS in the same domain, we require to map relevant information from the elevator knowledge base/ontology, such as component information, to a diagnostic problem solver, and then to extend it with diagnostic information such as malfunctions, symptoms and repairs for each component. We have developed MAKTab, a Protege plug-in which supports both these steps and results in a composite KBS which is executable.