Capturing expertise and enabling efficient information retrieval are critical in the energy sector, where high staff turnover can lead to significant knowledge loss. Retrieval Augmented Generation (RAG) offers a solution by grounding Large Language Model (LLM) outputs in documented sources, but its effectiveness is limited by reliance on general-purpose embeddings. We present Wikatoni, an agentic AI system for energy engineering workflows that integrates a novel domain-specific embedding model. Wikatoni combines fine-tuned embeddings with agentic RAG, metadata filtering, and hybrid retrieval to improve document search, automated reporting, and workflow efficiency. Evaluation on internal enterprise offshore energy data shows that the domain-adapted embedding improves recall by 10%, and Wikatoni agentic RAG further increases answer accuracy by 14% compared to vanilla RAG with the base embedding model, achieving the best overall performance in context recall, faithfulness, and answer accuracy.

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 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.