Research Papers

How Large Language Models Are Changing MOOC Essay Answers: A Comparison of Pre- and Post-LLM Responses

Leo Leppänen, Lili Aunimo, Arto Hellas +2

The release of ChatGPT in late 2022 caused a flurry of activity and concern in the academic and educational communities. Some see the tool's ability to generate human-like text that passes at least cursory inspections for factual accuracy ``often enough'' a golden age of information retrieval and computer-assisted learning. Some, on the other hand, worry the tool may lead to unprecedented levels of academic dishonesty and cheating. In this work, we quantify some of the effects of the emergence of Large Language Models (LLMs) on online education by analyzing a multi-year dataset of student essay responses from a free university-level MOOC on AI ethics. Our dataset includes essays submitted both before and after ChatGPT's release. We find that the launch of ChatGPT coincided with significant changes in both the length and style of student essays, mirroring observations in other contexts such as academic publishing. We also observe -- as expected based on related public discourse -- changes in prevalence of key content words related to AI and LLMs, but not necessarily the general themes or topics discussed in the student essays as identified through (dynamic) topic modeling.

As AI systems increasingly influence critical sectors like telecommunications, finance, healthcare, and public services, ensuring fairness in decision-making is essential to prevent biased or unjust outcomes that disproportionately affect vulnerable entities or result in adverse impacts. This need is particularly pressing as the industry approaches the 6G era, where AI will drive complex functions like autonomous network management and hyper-personalized services. The TEC Standard for Fairness Assessment and Rating of AI Systems provides guidelines for evaluating fairness in AI, focusing primarily on tabular data and supervised learning models. However, as AI applications diversify, this standard requires enhancement to strengthen its impact and broaden its applicability. This paper proposes an expansion of the TEC Standard to include fairness assessments for images, unstructured text, and generative AI, including large language models, ensuring a more comprehensive approach that keeps pace with evolving AI technologies. By incorporating these dimensions, the enhanced framework will promote responsible and trustworthy AI deployment across various sectors.

The malicious use or malfunction of advanced general-purpose AI (GPAI) poses risks that, according to leading experts, could lead to the 'marginalisation or extinction of humanity.' To address these risks, there are an increasing number of proposals for international agreements on AI safety. In this paper, we review recent (2023-) proposals, identifying areas of consensus and disagreement, and drawing on related literature to assess their feasibility. We focus our discussion on risk thresholds, regulations, types of international agreement and five related processes: building scientific consensus, standardisation, auditing, verification and incentivisation. Based on this review, we propose a treaty establishing a compute threshold above which development requires rigorous oversight. This treaty would mandate complementary audits of models, information security and governance practices, overseen by an international network of AI Safety Institutes (AISIs) with authority to pause development if risks are unacceptable. Our approach combines immediately implementable measures with a flexible structure that can adapt to ongoing research.

An Explainable Biomedical Foundation Model via Large-Scale Concept-Enhanced Vision-Language Pre-training

Yuxiang Nie, Sunan He, Yequan Bie +14

The clinical adoption of artificial intelligence (AI) in medical imaging requires models that are both diagnostically accurate and interpretable to clinicians. While current multimodal biomedical foundation models prioritize performance, their black-box nature hinders explaining the decision-making process in clinically meaningful concepts. Here, we present ConceptCLIP, the first explainable biomedical foundation model that achieves state-of-the-art diagnostic accuracy while delivering human-interpretable explanations across diverse imaging modalities. We curate MedConcept-23M, the largest pre-training dataset comprising 23 million image-text-concept triplets across diverse medical modalities, where clinical concepts are derived from the Unified Medical Language System. Leveraging this dataset, we develop ConceptCLIP through a novel dual-alignment approach that simultaneously learns global image-text representations and fine-grained region-concept associations for precise and interpretable medical image analysis. We curate the most extensive evaluation benchmark for multimodal biomedical foundation models, covering 52 clinical tasks spanning 10 imaging modalities. Extensive experiments demonstrate that ConceptCLIP outperforms existing state-of-the-art multimodal biomedical foundation models. Importantly, ConceptCLIP demonstrates superior diagnostic performance while providing human-understandable explanations validated by clinical experts. As the first precise and interpretable biomedical foundation model, ConceptCLIP represents a critical milestone toward the widespread clinical adoption of AI, thereby advancing trustworthy AI in medicine.

Where AI Assurance Might Go Wrong: Initial lessons from engineering of critical systems

Robin Bloomfield, John Rushby

We draw on our experience working on system and software assurance and evaluation for systems important to society to summarise how safety engineering is performed in traditional critical systems, such as aircraft flight control. We analyse how this critical systems perspective might support the development and implementation of AI Safety Frameworks. We present the analysis in terms of: system engineering, safety and risk analysis, and decision analysis and support. We consider four key questions: What is the system? How good does it have to be? What is the impact of criticality on system development? and How much should we trust it? We identify topics worthy of further discussion. In particular, we are concerned that system boundaries are not broad enough, that the tolerability and nature of the risks are not sufficiently elaborated, and that the assurance methods lack theories that would allow behaviours to be adequately assured. We advocate the use of assurance cases based on Assurance 2.0 to support decision making in which the criticality of the decision as well as the criticality of the system are evaluated. We point out the orders of magnitude difference in confidence needed in critical rather than everyday systems and how everyday techniques do not scale in rigour. Finally we map our findings in detail to two of the questions posed by the FAISC organisers and we note that the engineering of critical systems has evolved through open and diverse discussion. We hope that topics identified here will support the post-FAISC dialogues.

We investigate the connection between visual semantic features defined in PI-RADS and associated risk factors, moving beyond abnormal imaging findings, establishing a shared framework between medical and AI professionals by creating a standardized dictionary of biological/radiological RFs. Subsequently, 6 interpretable and seven complex classifiers, linked with nine interpretable feature selection algorithms (FSA) applied to risk factors, were extracted from segmented lesions in T2-weighted imaging (T2WI), diffusion-weighted imaging (DWI), and apparent diffusion coefficient (ADC) multiparametric-prostate MRI sequences to predict the UCLA scores. We then utilized the created dictionary to interpret the best-predictive models. Combining T2WI, DWI, and ADC with FSAs including ANOVA F-test, Correlation Coefficient, and Fisher Score, and utilizing logistic regression, identified key features: The 90th percentile from T2WI, which captures hypo-intensity related to prostate cancer risk; Variance from T2WI, indicating lesion heterogeneity; shape metrics including Least Axis Length and Surface Area to Volume ratio from ADC, describing lesion shape and compactness; and Run Entropy from ADC, reflecting texture consistency. This approach achieved the highest average accuracy of 0.78, significantly outperforming single-sequence methods (p-value<0.05). The developed dictionary for Prostate-MRI (PM1.0) serves as a common language, fosters collaboration between clinical professionals and AI developers to advance trustworthy AI solutions that support reliable/interpretable clinical decisions.

Trustworthy artificial intelligence in the energy sector: Landscape analysis and evaluation framework

Sotiris Pelekis, Evangelos Karakolis, George Lampropoulos +4

The present study aims to evaluate the current fuzzy landscape of Trustworthy AI (TAI) within the European Union (EU), with a specific focus on the energy sector. The analysis encompasses legal frameworks, directives, initiatives, and standards like the AI Ethics Guidelines for Trustworthy AI (EGTAI), the Assessment List for Trustworthy AI (ALTAI), the AI act, and relevant CEN-CENELEC standardization efforts, as well as EU-funded projects such as AI4EU and SHERPA. Subsequently, we introduce a new TAI application framework, called E-TAI, tailored for energy applications, including smart grid and smart building systems. This framework draws inspiration from EGTAI but is customized for AI systems in the energy domain. It is designed for stakeholders in electrical power and energy systems (EPES), including researchers, developers, and energy experts linked to transmission system operators, distribution system operators, utilities, and aggregators. These stakeholders can utilize E-TAI to develop and evaluate AI services for the energy sector with a focus on ensuring trustworthiness throughout their development and iterative assessment processes.

Medical image classification is crucial for supporting healthcare professionals in decision-making and training. While Convolutional Neural Networks (CNNs) have traditionally dominated this field, Transformer-based models are gaining attention. In this study, we apply explainable AI (XAI) techniques to assess the performance of various models on real-world medical data and identify areas for improvement. We compare CNN models such as VGG-16, ResNet-50, and EfficientNetV2L with a Transformer model: ViT-Base-16. Our results show that data augmentation has little impact, but hyperparameter tuning and advanced modeling improve performance. CNNs, particularly VGG-16 and ResNet-50, outperform ViT-Base-16 and EfficientNetV2L, likely due to underfitting from limited data. XAI methods like LIME and SHAP further reveal that better-performing models visualize tumors more effectively. These findings suggest that CNNs with shallower architectures are more effective for small datasets and can support medical decision-making.

Convolutional neural networks (CNNs) achieve prevailing results in segmentation tasks nowadays and represent the state-of-the-art for image-based analysis. However, the understanding of the accurate decision-making process of a CNN is rather unknown. The research area of explainable artificial intelligence (xAI) primarily revolves around understanding and interpreting this black-box behavior. One way of interpreting a CNN is the use of class activation maps (CAMs) that represent heatmaps to indicate the importance of image areas for the prediction of the CNN. For classification tasks, a variety of CAM algorithms exist. But for segmentation tasks, only one CAM algorithm for the interpretation of the output of a CNN exist. We propose a transfer between existing classification- and segmentation-based methods for more detailed, explainable, and consistent results which show salient pixels in semantic segmentation tasks. The resulting Seg-HiRes-Grad CAM is an extension of the segmentation-based Seg-Grad CAM with the transfer to the classification-based HiRes CAM. Our method improves the previously-mentioned existing segmentation-based method by adjusting it to recently published classification-based methods. Especially for medical image segmentation, this transfer solves existing explainability disadvantages.

Power grids serve as a vital component in numerous industries, seamlessly delivering electrical energy to industrial processes and technologies, making their safe and reliable operation indispensable. However, powerlines can be hard to inspect due to difficult terrain or harsh climatic conditions. Therefore, unmanned aerial vehicles are increasingly deployed to inspect powerlines, resulting in a substantial stream of visual data which requires swift and accurate processing. Deep learning methods have become widely popular for this task, proving to be a valuable asset in fault detection. In particular, the detection of insulator defects is crucial for predicting powerline failures, since their malfunction can lead to transmission disruptions. It is therefore of great interest to continuously maintain and rigorously inspect insulator components. In this work we propose a novel pipeline to tackle this task. We utilize state-of-the-art object detection to detect and subsequently classify individual insulator anomalies. Our approach addresses dataset challenges such as imbalance and motion-blurred images through a fine-tuning methodology which allows us to alter the classification focus of the model by increasing the classification accuracy of anomalous insulators. In addition, we employ explainable-AI tools for precise localization and explanation of anomalies. This proposed method contributes to the field of anomaly detection, particularly vision-based industrial inspection and predictive maintenance. We significantly improve defect detection accuracy by up to 13%, while also offering a detailed analysis of model mis-classifications and localization quality, showcasing the potential of our method on real-world data.

This study presents an explainable artificial intelligent (XAI) model for predicting pile driving vibrations in Bangkok's soft clay subsoil. A deep neural network was developed using a dataset of 1,018 real-world pile driving measurements, encompassing variations in pile dimensions, hammer characteristics, sensor locations, and vibration measurement axes. The model achieved a mean absolute error (MAE) of 0.276, outperforming traditional empirical methods and other machine learning approaches such as XGBoost and CatBoost. SHapley Additive exPlanations (SHAP) analysis was employed to interpret the model's predictions, revealing complex relationships between input features and peak particle velocity (PPV). Distance from the pile driving location emerged as the most influential factor, followed by hammer weight and pile size. Non-linear relationships and threshold effects were observed, providing new insights into vibration propagation in soft clay. A web-based application was developed to facilitate adoption by practicing engineers, bridging the gap between advanced machine learning techniques and practical engineering applications. This research contributes to the field of geotechnical engineering by offering a more accurate and nuanced approach to predicting pile driving vibrations, with implications for optimizing construction practices and mitigating environmental impacts in urban areas. The model and its source code are publicly available, promoting transparency and reproducibility in geotechnical research.

Knowing more about the data used to build AI systems is critical for allowing different stakeholders to play their part in ensuring responsible and appropriate deployment and use. Meanwhile, a 2023 report shows that data transparency lags significantly behind other areas of AI transparency in popular foundation models. In this research, we sought to build on these findings, exploring the status of public documentation about data practices within AI systems generating public concern. Our findings demonstrate that low data transparency persists across a wide range of systems, and further that issues of transparency and explainability at model- and system- level create barriers for investigating data transparency information to address public concerns about AI systems. We highlight a need to develop systematic ways of monitoring AI data transparency that account for the diversity of AI system types, and for such efforts to build on further understanding of the needs of those both supplying and using data transparency information.