Elizabeth Williams

Favour Yahdii Aghaebe, Tanefa Apekey, Elizabeth Williams et al.

Clinical interventions often hinge on age: medications and procedures safe for adults may be harmful to children or ineffective for older adults. However, as language models are increasingly integrated into biomedical evidence synthesis workflows, it remains uncertain whether these systems preserve such crucial demographic distinctions. To address this gap, we evaluate how well state-of-the-art language models retain age-related information when generating abstractive summaries of biomedical studies. We construct DemogSummary, a novel age-stratified dataset of systematic review primary studies, covering child, adult, and older adult populations. We evaluate three prominent summarisation-capable LLMs, Qwen (open-source), Longformer (open-source) and GPT-4.1 Nano (proprietary), using both standard metrics and a newly proposed Demographic Salience Score (DSS), which quantifies age-related entity retention and hallucination. Our results reveal systematic disparities across models and age groups: demographic fidelity is lowest for adult-focused summaries, and under-represented populations are more prone to hallucinations. These findings highlight the limitations of current LLMs in faithful and bias-free summarisation and point to the need for fairness-aware evaluation frameworks and summarisation pipelines in biomedical NLP.

Favour Yahdii Aghaebe, Tanefa Apekey, Elizabeth Williams et al.

Opinion and multi-document summarisation often involve genuinely conflicting viewpoints, yet many existing approaches, particularly LLM-based systems, implicitly smooth disagreement and over-represent majority opinions. This limits the faithfulness of generated summaries in opinion-heavy settings. We introduce a disagreement-aware synthesis pipeline that separates belief-level aggregation from language generation. Documents are first represented as structured belief sets and aggregated using distance-based belief merging operators that explicitly model conflict. Large language models are then used only to realise the aggregated beliefs as natural language summaries. We evaluate the approach across multiple model families and scales, comparing it to methods that perform explicit aggregation during generation. Our results show that while sufficiently large models can match belief-level aggregation when aggregation is handled at generation time, this behaviour is not stable across architectures or capacities. In contrast, belief-level aggregation combined with simple prompting yields consistently strong disagreement-aware performance across models, while maintaining fluent and grounded summaries.

Elizabeth Williams, Daniel Gartner, Paul Harper

Many economies are challenged by the effects of an ageing population, particularly in sectors where resource capacity planning is critical, such as healthcare. This research addresses the operational challenges of bed and staffing capacity planning in hospital wards by using predictive and prescriptive analytical methods, both individually and in tandem. We applied these methodologies to a study of 165,000 patients across a network of 11 hospitals in the UK. Predictive modelling, specifically Classification and Regression Trees, forecasts patient length of stay based on clinical and demographic data. On the prescriptive side, deterministic and two-stage stochastic optimisation models determine optimal bed and staff planning strategies to minimise costs. Linking the predictive models with the prescriptive optimisation models, generates demand forecasts that inform the optimisation process, providing accurate and practical solutions. The results demonstrate that this integrated approach captures real-world variations in patient LOS and offers a 7% cost saving compared to average-based planning. This approach helps healthcare managers make robust decisions by incorporating patient-specific characteristics, improving capacity allocation, and mitigating risks associated with demand variability. Consequently, this combined methodology can be broadly extended across various sectors facing similar challenges, showcasing the versatility and effectiveness of integrating predictive and prescriptive analytics.

Aditi Verma, Elizabeth Williams

AI models are rapidly becoming embedded in all aspects of nuclear energy research and work but the safety, security, and safeguards consequences of this embedding are not well understood. In this paper, we call for the creation of an anticipatory system of governance for AI in the nuclear sector as well as the creation of a global AI observatory as a means for operationalizing anticipatory governance. The paper explores the contours of the nuclear AI observatory and an anticipatory system of governance by drawing on work in science and technology studies, public policy, and foresight studies.