David Lillis

Yogesh Bansal, David Lillis, Mohand Tahar Kechadi

Western countries rely heavily on wheat, and yield prediction is crucial. Time-series deep learning models, such as Long Short Term Memory (LSTM), have already been explored and applied to yield prediction. Existing literature reported that they perform better than traditional Machine Learning (ML) models. However, the existing LSTM cannot handle heterogeneous datasets (a combination of data which varies and remains static with time). In this paper, we propose an efficient deep learning model that can deal with heterogeneous datasets. We developed the system architecture and applied it to the real-world dataset in the digital agriculture area. We showed that it outperforms the existing ML models.

Shushanta Pudasaini, Luis Miralles-Pechuán, David Lillis et al.

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.

Yogesh Bansal, David Lillis, Mohand Tahar Kechadi

Winter wheat is one of the most important crops in the United Kingdom, and crop yield prediction is essential for the nation's food security. Several studies have employed machine learning (ML) techniques to predict crop yield on a county or farm-based level. The main objective of this study is to predict winter wheat crop yield using ML models on multiple heterogeneous datasets, i.e., soil and weather on a zone-based level. Experimental results demonstrated their impact when used alone and in combination. In addition, we employ numerous ML algorithms to emphasize the significance of data quality in any machine-learning strategy.

Congcong Wang, David Lillis

In recent years, the task of mining important information from social media posts during crises has become a focus of research for the purposes of assisting emergency response (ES). The TREC Incident Streams (IS) track is a research challenge organised for this purpose. The track asks participating systems to both classify a stream of crisis-related tweets into humanitarian aid related information types and estimate their importance regarding criticality. The former refers to a multi-label information type classification task and the latter refers to a priority estimation task. In this paper, we report on the participation of the University College Dublin School of Computer Science (UCD-CS) in TREC-IS 2021. We explored a variety of approaches, including simple machine learning algorithms, multi-task learning techniques, text augmentation, and ensemble approaches. The official evaluation results indicate that our runs achieve the highest scores in many metrics. To aid reproducibility, our code is publicly available at https://github.com/wangcongcong123/crisis-mtl.

Congcong Wang, Paul Nulty, David Lillis

User-generated content (UGC) on social media can act as a key source of information for emergency responders in crisis situations. However, due to the volume concerned, computational techniques are needed to effectively filter and prioritise this content as it arises during emerging events. In the literature, these techniques are trained using annotated content from previous crises. In this paper, we investigate how this prior knowledge can be best leveraged for new crises by examining the extent to which crisis events of a similar type are more suitable for adaptation to new events (cross-domain adaptation). Given the recent successes of transformers in various language processing tasks, we propose CAST: an approach for Crisis domain Adaptation leveraging Sequence-to-sequence Transformers. We evaluate CAST using two major crisis-related message classification datasets. Our experiments show that our CAST-based best run without using any target data achieves the state of the art performance in both in-domain and cross-domain contexts. Moreover, CAST is particularly effective in one-to-one cross-domain adaptation when trained with a larger language model. In many-to-one adaptation where multiple crises are jointly used as the source domain, CAST further improves its performance. In addition, we find that more similar events are more likely to bring better adaptation performance whereas fine-tuning using dissimilar events does not help for adaptation. To aid reproducibility, we open source our code to the community.

Oisin Suttle, David Lillis

As Large Language Models (LLMs) are proposed as legal decision assistants, and even first-instance decision-makers, across a range of judicial and administrative contexts, it becomes essential to explore how they answer legal questions, and in particular the factors that lead them to decide difficult questions in one way or another. A specific feature of legal decisions is the need to respond to arguments advanced by contending parties. A legal decision-maker must be able to engage with, and respond to, including through being potentially persuaded by, arguments advanced by the parties. Conversely, they should not be unduly persuadable, influenced by a particularly compelling advocate to decide cases based on the skills of the advocates, rather than the merits of the case. We explore how frontier open- and closed-weights LLMs respond to legal arguments, reporting original experimental results examining how the quality of the advocate making those arguments affects the likelihood that a model will agree with a particular legal point of view, and exploring the factors driving these results. Our results have implications for the feasibility of adopting LLMs across legal and administrative settings.

Sargam Yadav, Asifa Mehmood Qureshi, Abhishek Kaushik et al.

The introduction of transformer architecture was a turning point in Natural Language Processing (NLP). Models based on the transformer architecture such as Bidirectional Encoder Representations from Transformers (BERT) and Generative Pre-Trained Transformer (GPT) have gained widespread popularity in various applications such as software development and education. The availability of Large Language Models (LLMs) such as ChatGPT and Bard to the general public has showcased the tremendous potential of these models and encouraged their integration into various domains such as software development for tasks such as code generation, debugging, and documentation generation. In this study, opinions from 11 experts regarding their experience with LLMs for software development have been gathered and analysed to draw insights that can guide successful and responsible integration. The overall opinion of the experts is positive, with the experts identifying advantages such as increase in productivity and reduced coding time. Potential concerns and challenges such as risk of over-dependence and ethical considerations have also been highlighted.

Abhishek Kaushik, Sargam Yadav, Andrew Browne et al.

The recent advancements in Generative Artificial intelligence (GenAI) technology have been transformative for the field of education. Large Language Models (LLMs) such as ChatGPT and Bard can be leveraged to automate boilerplate tasks, create content for personalised teaching, and handle repetitive tasks to allow more time for creative thinking. However, it is important to develop guidelines, policies, and assessment methods in the education sector to ensure the responsible integration of these tools. In this article, thematic analysis has been performed on seven essays obtained from professionals in the education sector to understand the advantages and pitfalls of using GenAI models such as ChatGPT and Bard in education. Exploratory Data Analysis (EDA) has been performed on the essays to extract further insights from the text. The study found several themes which highlight benefits and drawbacks of GenAI tools, as well as suggestions to overcome these limitations and ensure that students are using these tools in a responsible and ethical manner.

Shushanta Pudasaini, Luis Miralles-Pechuán, David Lillis et al.

The rise of Large Language Models (LLMs) such as ChatGPT and Gemini has posed new challenges for the academic community. With the help of these models, students can easily complete their assignments and exams, while educators struggle to detect AI-generated content. This has led to a surge in academic misconduct, as students present work generated by LLMs as their own, without putting in the effort required for learning. As AI tools become more advanced and produce increasingly human-like text, detecting such content becomes more challenging. This development has significantly impacted the academic world, where many educators are finding it difficult to adapt their assessment methods to this challenge. This research first demonstrates how LLMs have increased academic dishonesty, and then reviews state-of-the-art solutions for academic plagiarism in detail. A survey of datasets, algorithms, tools, and evasion strategies for plagiarism detection has been conducted, focusing on how LLMs and AI-generated content (AIGC) detection have affected this area. The survey aims to identify the gaps in existing solutions. Lastly, potential long-term solutions are presented to address the issue of academic plagiarism using LLMs based on AI tools and educational approaches in an ever-changing world.

Gechuan Zhang, Paul Nulty, David Lillis

The contextual word embedding model, BERT, has proved its ability on downstream tasks with limited quantities of annotated data. BERT and its variants help to reduce the burden of complex annotation work in many interdisciplinary research areas, for example, legal argument mining in digital humanities. Argument mining aims to develop text analysis tools that can automatically retrieve arguments and identify relationships between argumentation clauses. Since argumentation is one of the key aspects of case law, argument mining tools for legal texts are applicable to both academic and non-academic legal research. Domain-specific BERT variants (pre-trained with corpora from a particular background) have also achieved strong performance in many tasks. To our knowledge, previous machine learning studies of argument mining on judicial case law still heavily rely on statistical models. In this paper, we provide a broad study of both classic and contextual embedding models and their performance on practical case law from the European Court of Human Rights (ECHR). During our study, we also explore a number of neural networks when being combined with different embeddings. Our experiments provide a comprehensive overview of a variety of approaches to the legal argument mining task. We conclude that domain pre-trained transformer models have great potential in this area, although traditional embeddings can also achieve strong performance when combined with additional neural network layers.

Congcong Wang, Paul Nulty, David Lillis

Social media has enabled people to circulate information in a timely fashion, thus motivating people to post messages seeking help during crisis situations. These messages can contribute to the situational awareness of emergency responders, who have a need for them to be categorised according to information types (i.e. the type of aid services the messages are requesting). We introduce a transformer-based multi-task learning (MTL) technique for classifying information types and estimating the priority of these messages. We evaluate the effectiveness of our approach with a variety of metrics by submitting runs to the TREC Incident Streams (IS) track: a research initiative specifically designed for disaster tweet classification and prioritisation. The results demonstrate that our approach achieves competitive performance in most metrics as compared to other participating runs. Subsequently, we find that an ensemble approach combining disparate transformer encoders within our approach helps to improve the overall effectiveness to a significant extent, achieving state-of-the-art performance in almost every metric. We make the code publicly available so that our work can be reproduced and used as a baseline for the community for future work in this domain.

Congcong Wang, David Lillis

The Incident streams (IS) track is a research challenge aimed at finding important information from social media during crises for emergency response purposes. More specifically, given a stream of crisis-related tweets, the IS challenge asks a participating system to 1) classify what the types of users' concerns or needs are expressed in each tweet, known as the information type (IT) classification task and 2) estimate how critical each tweet is with regard to emergency response, known as the priority level prediction task. In this paper, we describe our multi-task transfer learning approach for this challenge. Our approach leverages state-of-the-art transformer models including both encoder-based models such as BERT and a sequence-to-sequence based T5 for joint transfer learning on the two tasks. Based on this approach, we submitted several runs to the track. The returned evaluation results show that our runs substantially outperform other participating runs in both IT classification and priority level prediction.

Felix Anda, Brett A. Becker, David Lillis et al.

Swift response to the detection of endangered minors is an ongoing concern for law enforcement. Many child-focused investigations hinge on digital evidence discovery and analysis. Automated age estimation techniques are needed to aid in these investigations to expedite this evidence discovery process, and decrease investigator exposure to traumatic material. Automated techniques also show promise in decreasing the overflowing backlog of evidence obtained from increasing numbers of devices and online services. A lack of sufficient training data combined with natural human variance has been long hindering accurate automated age estimation -- especially for underage subjects. This paper presented a comprehensive evaluation of the performance of two cloud age estimation services (Amazon Web Service's Rekognition service and Microsoft Azure's Face API) against a dataset of over 21,800 underage subjects. The objective of this work is to evaluate the influence that certain human biometric factors, facial expressions, and image quality (i.e. blur, noise, exposure and resolution) have on the outcome of automated age estimation services. A thorough evaluation allows us to identify the most influential factors to be overcome in future age estimation systems.

Congcong Wang, David Lillis

In this paper, we describe our approach in the shared task: COVID-19 event extraction from Twitter. The objective of this task is to extract answers from COVID-related tweets to a set of predefined slot-filling questions. Our approach treats the event extraction task as a question answering task by leveraging the transformer-based T5 text-to-text model. According to the official evaluation scores returned, namely F1, our submitted run achieves competitive performance compared to other participating runs (Top 3). However, we argue that this evaluation may underestimate the actual performance of runs based on text-generation. Although some such runs may answer the slot questions well, they may not be an exact string match for the gold standard answers. To measure the extent of this underestimation, we adopt a simple exact-answer transformation method aiming at converting the well-answered predictions to exactly-matched predictions. The results show that after this transformation our run overall reaches the same level of performance as the best participating run and state-of-the-art F1 scores in three of five COVID-related events. Our code is publicly available to aid reproducibility

Felix Anda, David Lillis, Aikaterini Kanta et al.

Achieving high performance for facial age estimation with subjects in the borderline between adulthood and non-adulthood has always been a challenge. Several studies have used different approaches from the age of a baby to an elder adult and different datasets have been employed to measure the mean absolute error (MAE) ranging between 1.47 to 8 years. The weakness of the algorithms specifically in the borderline has been a motivation for this paper. In our approach, we have developed an ensemble technique that improves the accuracy of underage estimation in conjunction with our deep learning model (DS13K) that has been fine-tuned on the Deep Expectation (DEX) model. We have achieved an accuracy of 68% for the age group 16 to 17 years old, which is 4 times better than the DEX accuracy for such age range. We also present an evaluation of existing cloud-based and offline facial age prediction services, such as Amazon Rekognition, Microsoft Azure Cognitive Services, How-Old.net and DEX.

Weinan Huang, Junyi Chen, Lei Meng et al.

Combining the results of different search engines in order to improve upon their performance has been the subject of many research papers. This has become known as the "Data Fusion" task, and has great promise in dealing with the vast quantity of unstructured textual data that is a feature of many Big Data scenarios. However, no universally-accepted evaluation methodology has emerged in the community. This makes it difficult to make meaningful comparisons between the various proposed techniques from reading the literature alone. Variations in the datasets, metrics, and baseline results have all contributed to this difficulty. This paper argues that a more unified approach is required, and that a centralised software platform should be developed to aid researchers in making comparisons between their algorithms and others. The desirable qualities of such a system have been identified and proposed, and an early prototype has been developed. Re-implementing algorithms published by other researchers is a great burden on those proposing new techniques. The prototype system has the potential to greatly reduce this burden and thus encourage more comparable results being generated and published more easily.

David Lillis, Frank Breitinger, Mark Scanlon

Bytewise approximate matching algorithms have in recent years shown significant promise in de- tecting files that are similar at the byte level. This is very useful for digital forensic investigators, who are regularly faced with the problem of searching through a seized device for pertinent data. A common scenario is where an investigator is in possession of a collection of "known-illegal" files (e.g. a collection of child abuse material) and wishes to find whether copies of these are stored on the seized device. Approximate matching addresses shortcomings in traditional hashing, which can only find identical files, by also being able to deal with cases of merged files, embedded files, partial files, or if a file has been changed in any way. Most approximate matching algorithms work by comparing pairs of files, which is not a scalable approach when faced with large corpora. This paper demonstrates the effectiveness of using a "Hierarchical Bloom Filter Tree" (HBFT) data structure to reduce the running time of collection-against-collection matching, with a specific focus on the MRSH-v2 algorithm. Three experiments are discussed, which explore the effects of different configurations of HBFTs. The proposed approach dramatically reduces the number of pairwise comparisons required, and demonstrates substantial speed gains, while maintaining effectiveness.

Mark Scanlon, Xiaoyu Du, David Lillis

Education and training in digital forensics requires a variety of suitable challenge corpora containing realistic features including regular wear-and-tear, background noise, and the actual digital traces to be discovered during investigation. Typically, the creation of these challenges requires overly arduous effort on the part of the educator to ensure their viability. Once created, the challenge image needs to be stored and distributed to a class for practical training. This storage and distribution step requires significant time and resources and may not even be possible in an online/distance learning scenario due to the data sizes involved. As part of this paper, we introduce a more capable methodology and system as an alternative to current approaches. EviPlant is a system designed for the efficient creation, manipulation, storage and distribution of challenges for digital forensics education and training. The system relies on the initial distribution of base disk images, i.e., images containing solely base operating systems. In order to create challenges for students, educators can boot the base system, emulate the desired activity and perform a "diffing" of resultant image and the base image. This diffing process extracts the modified artefacts and associated metadata and stores them in an "evidence package". Evidence packages can be created for different personae, different wear-and-tear, different emulated crimes, etc., and multiple evidence packages can be distributed to students and integrated into the base images. A number of additional applications in digital forensic challenge creation for tool testing and validation, proficiency testing, and malware analysis are also discussed as a result of using EviPlant.

David Lillis, Brett Becker, Tadhg O'Sullivan et al.

Given the ever-increasing prevalence of technology in modern life, there is a corresponding increase in the likelihood of digital devices being pertinent to a criminal investigation or civil litigation. As a direct consequence, the number of investigations requiring digital forensic expertise is resulting in huge digital evidence backlogs being encountered by law enforcement agencies throughout the world. It can be anticipated that the number of cases requiring digital forensic analysis will greatly increase in the future. It is also likely that each case will require the analysis of an increasing number of devices including computers, smartphones, tablets, cloud-based services, Internet of Things devices, wearables, etc. The variety of new digital evidence sources pose new and challenging problems for the digital investigator from an identification, acquisition, storage and analysis perspective. This paper explores the current challenges contributing to the backlog in digital forensics from a technical standpoint and outlines a number of future research topics that could greatly contribute to a more efficient digital forensic process.

Dinh Doan Van Bien, David Lillis, Rem W. Collier

The design, implementation and testing of Multi Agent Systems is typically a very complex task. While a number of specialist agent programming languages and toolkits have been created to aid in the development of such systems, the provision of associated development tools still lags behind those available for other programming paradigms. This includes tools such as debuggers and profilers to help analyse system behaviour, performance and efficiency. AgentSpotter is a profiling tool designed specifically to operate on the concepts of agent-oriented programming. This paper extends previous work on AgentSpotter by discussing its Call Graph View, which presents system performance information, with reference to the communication between the agents in the system. This is aimed at aiding developers in examining the effect that agent communication has on the processing requirements of the system.

Dinh Doan Van Bien, David Lillis, Rem W. Collier

Advances in Agent Oriented Software Engineering have focused on the provision of frameworks and toolkits to aid in the creation of Multi Agent Systems (MASs). However, despite the need to address the inherent complexity of such systems, little progress has been made in the development of tools to allow for the debugging and understanding of their inner workings. This paper introduces a novel performance analysis system, named AgentSpotter, which facilitates such analysis. AgentSpotter was developed by mapping conventional profiling concepts to the domain of MASs. We outline its integration into the Agent Factory multi agent framework.

David Lillis, Fergus Toolan, Rem W. Collier et al.

Recent developments in the field of data fusion have seen a focus on techniques that use training queries to estimate the probability that various documents are relevant to a given query and use that information to assign scores to those documents on which they are subsequently ranked. This paper introduces SlideFuse, which builds on these techniques, introducing a sliding window in order to compensate for situations where little relevance information is available to aid in the estimation of probabilities. SlideFuse is shown to perform favourably in comparison with CombMNZ, ProbFuse and SegFuse. CombMNZ is the standard baseline technique against which data fusion algorithms are compared whereas ProbFuse and SegFuse represent the state-of-the-art for probabilistic data fusion methods.

David Lillis, Rem Collier, Mauro Dragone et al.

This paper details the implementation of a software framework that aids the development of distributed and self-configurable software systems. This framework is an instance of a novel integration strategy called SoSAA (SOcially Situated Agent Architecture), which combines Component-Based Software Engineering and Agent-Oriented Software Engineering, drawing its inspiration from hybrid agent control architectures. The framework defines a complete construction process by enhancing a simple component-based framework with reasoning and self-awareness capabilities through a standardized interface. The capabilities of the resulting framework are demonstrated through its application to a non-trivial Multi Agent System (MAS). The system in question is a pre-existing Information Retrieval (IR) system that has not previously taken advantage of CBSE principles. In this paper we contrast these two systems so as to highlight the benefits of using this new hybrid approach. We also outline how component-based elements may be integrated into the Agent Factory agent-oriented application framework.

David Lillis, Fergus Toolan, Rem Collier et al.

Data fusion is the combination of the results of independent searches on a document collection into one single output result set. It has been shown in the past that this can greatly improve retrieval effectiveness over that of the individual results. This paper presents probFuse, a probabilistic approach to data fusion. ProbFuse assumes that the performance of the individual input systems on a number of training queries is indicative of their future performance. The fused result set is based on probabilities of relevance calculated during this training process. Retrieval experiments using data from the TREC ad hoc collection demonstrate that probFuse achieves results superior to that of the popular CombMNZ fusion algorithm.