Language models and software tools are essential to support the continuing vitality of lesser-used languages; however, currently popular neural models require considerable data for training, which normally is not available for such low-resource languages. This paper describes work-in-progress to construct a rule-based model of Gaidhlig morphology using data from Wiktionary, arguing that rule-based systems effectively leverage limited sample data, support greater interpretability, and provide insights useful in the design of teaching materials. The use of SQL for querying the occurrence of different lexical patterns is investigated, and a declarative rule-base is presented that allows Python utilities to derive inflected forms of Gaidhlig words. This functionality could be used to support educational tools that teach or explain language patterns, for example, or to support higher level tools such as rule-based dependency parsers. This approach adds value to the data already present in Wiktionary by adapting it to new use-cases.

A comprehensive Training Needs Analysis (TNA) is essential for effective HR development and organisational growth. However, traditional approaches often fall short due to limitations in scale, labour intensity, resource constraints, or expertise. To address these challenges, we propose an AI-driven automated platform for conducting TNA at scale with unstructured data. Our prototype features a dual-agent system, where the Disseminator Agent performs knowledge extraction and deep data analysis, followed by the Formulator Agent producing novel intellectual ideas, actionable insights, and formatted TNA reports, facilitating final human verification, attestation, and decision-making. We also outline a pragmatic plan for AI monitoring and platform evaluation—critical components for successful AI adoption in industrial settings. Our proposed design is currently being implemented for evaluation and for its future deployment in a business setting.

We consider the problem of distinguishing human-written creative fiction (excerpts from novels) from similar text generated by an LLM. Our results show that, while human observers perform poorly (near chance levels) on this binary classification task, a variety of machine-learning models achieve accuracy in the range 0.93-0.98 over a previously unseen test set, even using only short samples and single-token (unigram) features. We therefore employ an inherently interpretable (linear) classifier (with a test accuracy of 0.98), in order to elucidate the underlying reasons for this high accuracy. In our analysis, we identify specific unigram features indicative of LLM-generated text, one of the most important being that the LLM tends to use a larger variety of synonyms, thereby skewing the probability distributions in a manner that is easy to detect for a machine learning classifier, yet very difficult for a human observer. Four additional explanation categories were also identified, namely, temporal drift, Americanisms, foreign language usage, and colloquialisms. As identification of the AI-generated text depends on a constellation of such features, the classification appears robust, and therefore not easy to circumvent by malicious actors intent on misrepresenting AI-generated text as human work.

Abstract While several studies have examined the security of code generated by GPT and other Large Language Models (LLMs), most have relied on controlled experiments rather than real developer interactions. This paper investigates the security of GPT-generated code extracted from the DevGPT dataset and evaluates the ability of current LLMs to detect and repair vulnerabilities in this real-world context. We analysed 2,315 C, C++, and C# code snippets using static scanners combined with manual inspection, identifying 56 vulnerabilities across 48 files. These files were then assessed using GPT-4.1, GPT-5, and Claude Opus 4.1 to determine whether these could identify the security issues and, where applicable, to specify the corresponding Common Weakness Enumeration (CWE) numbers and propose fixes. Manual review and re-scanning of the modified code showed that GPT-4.1, GPT-5, and Claude Opus 4.1 correctly detected 46, 44, and 45 vulnerabilities, and successfully repaired 42, 44, and 43 respectively. A comparison of experiments conducted in October 2024 and September 2025 indicates substantial progress, with overall detection and remediation rates improving from roughly 50% to around 75–80%. We also observe that LLM-generated code is about as likely to contain vulnerabilities as developer-written code, and that LLMs may confidently provide incorrect information, posing risks for less experienced developers.

Following the universal availability of generative AI systems with the release of ChatGPT, automatic detection of deceptive text created by Large Language Models has focused on domains such as academic plagiarism and “fake news”. However, generative AI also poses a threat to the livelihood of creative writers, and perhaps to literary culture in general, through reduction in quality of published material. Training a Large Language Model on writers’ output to generate “sham books” in a particular style seems to constitute a new form of plagiarism. This problem has been little researched. In this study, we trained Machine Learning classifier models to distinguish short samples of human-written from machine-generated creative fiction, focusing on classic detective novels. Our results show that a Na ̈ıve Bayes and a Multi-Layer Perceptron classifier achieved a high degree of success (accuracy > 95%), significantly outperforming human judges (accuracy < 55%). This approach worked well with short text samples (around 100 words), which previous research has shown to be difficult to classify. We have deployed an online proof-of-concept classifier tool, AI Detective, as a first step towards developing lightweight and reliable applications for use by editors and publishers, with the aim of protecting the economic and cultural contribution of human authors.

Implicit gender bias in Large Language Models (LLMs) is a well-documented problem that needs to be better understood in order to be addressed effectively. Implications of gender introduced into automatic translations can perpetuate real-world biases in Software Engineering and other domains. However, some LLMs use heuristics or post-processing to mask such bias, which makes investigation more difficult. Here, we examine bias in language models via back-translation, using the DeepL online translation service to investigate the bias evinced when repeatedly translating a set of 56 Software Engineering tasks used in a previous study. Each statement starts with ‘she’, and is translated first into a ‘genderless’ intermediate language then back into English; we then examine pronoun-choice in the back-translated texts. We believe this approach provides a useful alternative to large-scale surveys in mapping biases. We expand prior research in the following ways: (1) by comparing results across five intermediate languages, namely Finnish, Indonesian, Estonian, Turkish and Hungarian; (2) by proposing a novel metric for assessing the variation in gender implied in repeated translations of the same phrase, avoiding the over-interpretation of individual pronouns, apparent in earlier work; (3) by investigating sentence features that drive bias; (4) and by comparing results from three time-lapsed datasets to establish the reproducibility of the approach. We found that some languages display similar patterns of pronoun use, falling into three loose groups, but that patterns vary between groups; this underlines the need to work with multiple languages. We also identify the main verb appearing in a sentence as a likely significant driver of implied gender in the translations. Moreover, we see a good level of replicability in the results, and establish that our variation metric proves robust despite an obvious change in the behaviour of the DeepL translation API during the course of the study. These results show that the back-translation method can provide further insights into bias in language models.

Bias in Large Language Models (LLMs) has significant implications. Since they have revolutionized content creation on the web, they can lead to more unfair outcomes, lack of inclusivity, reinforcement of stereotypes and ethical and legal concerns. Notably, OpenAI has recently made claims they have introduced a new technique to ensure that DALL-E-2 generates images of people accurately reflect the diversity of the world’s population. In order to investigate bias within the field of Software Engineering, the study utilized DALL-E-2 image generation to assess 56 tasks related to software engineering. Another objective was to determine the impact of OpenAI’s new measures on the generated images for these specific tasks. Two sets of experiments were conducted. In one set, the tasks were prefixed with the clause "As a Software Engineer," while in the other set, only the tasks themselves were used. The tasks were presented in a gender-neutral manner, and the AI was instructed to generate images for each task 20 times. For a female-dominant task of doing administrative tasks, 40 more images were generated. The study revealed a large gender bias in the 2,280 images generated. For instance, in the subset of experiments with prompts explicitly incorporating the phrase "As a software engineer," only 2% of the generated images portrayed female protagonists. In all the images in this setting, male protagonists were dominant and in 45 tasks 100% of the protagonists were male. Notably, images generated without the prefixed clause only had more female protagonists in ‘provide comments on project milestones’ and ‘provide enhancements’, while other tasks did not exhibit a similar pattern. The findings emphasize unsuitability of implemented guardrails and the importance of further research on LLMs assessments. Further research is needed in LLMs to find out where their guardrails fail so companies can address them properly.

The operation of drilling rigs is highly expensive. It is therefore important to be able to identify and analyse factors affecting rig operations. We investigate the use of two Genetic Algorithms, K2GA and ChainGA, to induce a Bayesian Network model for the real world problem of Rig Operations Management. We sample from a unique dataset derived from the commercial market intelligence databases assembled by ODS-Petrodata Ltd. We observe a trade-off between K2GA, which finds significantly better scoring networks on our dataset, and ChainGA, which uses only one quarter of the computation time. We analyse the best structures produced from an industry standpoint and conclude by outlining a few potential applications of the models to support rig operations.

Model-based user interface development environments show promise for improving the productivity of user interface developers, and possibly for improving the quality of developed interfaces. While model-based techniques have previously been applied to the area of database interfaces, they have not been specifically targeted at the important area of object database applications. Such applications make use of models that are semantically richer than their relational counterparts in terms of both data structures and application functionality. In general, model-based techniques have not addressed how the information referenced in such applications is manifested within the described models, and is utilised within the generated interface itself. This lack of experience with such systems has led to many model-based projects providing minimal support for certain features that are essential to such data intensive applications, and has prevented object database interface developers in particular from benefiting from model-based techniques. This paper presents the Teallach model-based user interface development environment for object databases, describing the models it supports, the relationships between these models, the tool used to construct interfaces using the models and the generation of Java programs from the declarative models. Distinctive features of Teallach include comprehensive facilities for linking models, a flexible development method, an open architecture, and the generation of running applications based on the models constructed by designers. © 2001 Elsevier Science B.V. All rights reserved.

This short paper describes the presentation model used by the Teallach model-based user-interface development environment. Teallach's presentation model provides both abstract and concrete interactors, which are first-class objects that may be freely intermixed when building a user-interface. An example is provided showing this approach in use.

M.R. Pullen et al. (2000) have designed a new model of plant taxonomy (called Prometheus); it supports multiple overlapping classifications, and distinguishes the process of naming from classifying. The concepts identified in this taxonomic model necessitated the design of a new database model - the Prometheus Object-Oriented Model (POOM) - to represent and manipulate the data. POOM is an extended object-oriented model which emphasises relationships, thereby providing graph behaviour in an object-oriented database and providing an expressive means of defining relationships between objects. Additionally, the Object Query Language (OQL) is extended to the Prometheus Object-Oriented Language (POOL) in order to provide unified querying of object-oriented graph structures. This paper presents a taxonomic database system designed in terms of the concepts offered by POOM. Through examples we show how the representation of the semantics and processes of taxonomy, not possible using existing data models, can be supported. Example POOL queries highlight the need for the extended features for manipulating relationships, graph structures and complex objects such as are found in taxonomies.

This paper presents the work carried out in the Prometheus project and its motivation, taxonomy. Taxonomy presents challenges to common database systems. Because of its complexity and the necessary treatments applied to its data, common database model such as the relational, the object-oriented of even graph models are not able to support taxonomic applications fully. Our approach is the extension of a object-oriented database model with explicit relationships in order to support new features and thereby offer the necessary level of service for developing taxonomic applications.