I stand in the darkened silence of a rectangular chamber, 8 meters long and 6 meters wide, balanced on the tips of my toes. On the wall in front of me are the outlines of two circles. Beyond these walls is an enormous insulated hangar decked with artificial grass and filled with highly paid professional soccer players. I brace, as though waiting for the Death Star to ready its superlaser. I turn, and it takes another two touches before I've brought the ball fully under my control. A professional player would have managed it in one, and would have done so without making a sound.

Half a billion people worldwide live with diabetes. There are different types with different causes, but all lead people to have too much sugar in their blood. If not well controlled, this excess glucose can inflict damage throughout the body, putting people at risk of gum disease, nerve damage, kidney disease, blindness, amputations, heart attack, stroke and cancer. For now, patients manage the condition with medicines, insulin and lifestyle changes, but a new generation of treatments could reverse the disease. Details of the first woman treated for type 1 diabetes with stem cells taken from her own body were announced last month.

The extraction of essential news elements through the 5W1H framework (\textit{What}, \textit{When}, \textit{Where}, \textit{Why}, \textit{Who}, and \textit{How}) is critical for event extraction and text summarization. The advent of Large language models (LLMs) such as ChatGPT presents an opportunity to address language-related tasks through simple prompts without fine-tuning models with much time. While ChatGPT has encountered challenges in processing longer news texts and analyzing specific attributes in context, especially answering questions about \textit{What}, \textit{Why}, and \textit{How}. The effectiveness of extraction tasks is notably dependent on high-quality human-annotated datasets. However, the absence of such datasets for the 5W1H extraction increases the difficulty of fine-tuning strategies based on open-source LLMs. To address these limitations, first, we annotate a high-quality 5W1H dataset based on four typical news corpora (\textit{CNN/DailyMail}, \textit{XSum}, \textit{NYT}, \textit{RA-MDS}); second, we design several strategies from zero-shot/few-shot prompting to efficient fine-tuning to conduct 5W1H aspects extraction from the original news documents. The experimental results demonstrate that the performance of the fine-tuned models on our labelled dataset is superior to the performance of ChatGPT. Furthermore, we also explore the domain adaptation capability by testing the source-domain (e.g. NYT) models on the target domain corpus (e.g. CNN/DailyMail) for the task of 5W1H extraction.

Improving factual consistency in abstractive summarization has been a focus of current research. One promising approach is the post-editing method. However, previous works have yet to make sufficient use of factual factors in summaries and suffers from the negative effect of the training datasets. In this paper, we first propose a novel factual error correction model FactCloze based on a conditional-generation cloze task. FactCloze can construct the causality among factual factors while being able to determine whether the blank can be answered or not. Then, we propose a data distillation method to generate a more faithful summarization dataset SummDSC via multiple-dimensional evaluation. We experimentally validate the effectiveness of our approach, which leads to an improvement in multiple factual consistency metrics compared to baselines.

Single cell analysis of human skeletal muscle (SM) tissue cross-sections is a fundamental tool for understanding many neuromuscular disorders. For this analysis to be reliable and reproducible, identification of individual fibres within microscopy images (segmentation) of SM tissue should be automatic and precise. Biomedical scientists in this field currently rely on custom tools and general machine learning (ML) models, both followed by labour intensive and subjective manual interventions to fine-tune segmentation. We believe that fully automated, precise, reproducible segmentation is possible by training ML models. However, in this important biomedical domain, there are currently no good quality, publicly available annotated imaging datasets available for ML model training. In this paper we release NCL-SM: a high quality bioimaging dataset of 46 human SM tissue cross-sections from both healthy control subjects and from patients with genetically diagnosed muscle pathology. These images include $>$ 50k manually segmented muscle fibres (myofibres). In addition we also curated high quality myofibre segmentations, annotating reasons for rejecting low quality myofibres and low quality regions in SM tissue images, making these annotations completely ready for downstream analysis. This, we believe, will pave the way for development of a fully automatic pipeline that identifies individual myofibres within images of tissue sections and, in particular, also classifies individual myofibres that are fit for further analysis.

Large language models (LLMs) have produced notable breakthroughs in downstream performance [61; 11; 19; 62; 91; 49; 8; 78], but have also introduced new challenges in model evaluation. The success of LLMs has initiated a fundamental paradigm shift away from small specialized models designed for single tasks to universal models expected to perform well across a wide range of tasks. This shift has also posed an existential challenge for evaluation, with a need to move away from solely task-specific automatic metrics of evaluation and increasing reliance on human evaluation. While automatic metrics offer a degree of objectivity and reproducibility, alongside the benefits of speed and cost-effectiveness, they often fall short in fully capturing the complexities and nuances of natural language [48; 68]. Moreover, automatic metrics often rely on auxiliary models which introduce potential points of failure and unexpected challenges over time [58]. For example, reference-based metrics such as BLEU [54] and ROUGE [45] are usually poor indicators of human judgment, as they emphasize lexical overlap and struggle to account for the diverse expressions inherent in semantic representation [34; 84; 9].

The UK is home to 92 counties, each with its own distinctive look and feel. Now, a film editor has tasked artificial intelligence (AI) with putting faces to these counties - with hilarious results. Duncan Thomsen, 53, used the software Midjourney to create images of'average people' in 13 counties. The results suggest that the average residents in County Antrim are young with red hair, while people living in Anglesey are elderly (and wrapped up for the cold weather!). So, do you agree with what AI thinks the average people look like in your county?

A new method to assess the quality of organs for donation is set to revolutionise the transplant system – and it could help save lives and tens of millions of pounds. The National Institute for Health and Care Research (NIHR) is contributing more than £1 million in funding to develop the new technology, which is known as Organ Quality Assessment (OrQA). It works in the same way as Artificial Intelligence-based facial recognition to evaluate the quality of an organ. It is estimated the technology could result in up to 200 more patients receiving kidney transplants and 100 more receiving liver transplants a year in the UK. Colin Wilson, transplant surgeon at Newcastle upon Tyne Hospitals NHS Foundation Trust and co-lead of the project, said: "Transplantation is the best treatment for patients with organ failure, but unfortunately some organs can't be used due to concerns they won't function properly once transplanted. "The software we have developed'scores' the quality of the organ and aims to support surgeons to assess if the organ is healthy enough to be transplanted.

Waiters, shelf stackers and people working in retail are the most likely to be replaced by automated systems in the future, according to new research into AI employment. The study, funded by trade electrical suppliers ElectricalDirect, found that while manual and repetitive tasks were easy to replace with robots, doctors and teachers were safe'for now'. The jobs most at risk from automation, according to the study, are waiters, shelf fillers, retail assistants, bar staff and farm workers. At the other end of the scale, with those in the most'secure from automation' roles are doctors, teachers, dentists, psychologists and physiotherapists. The researchers found an obvious geographical trend as well, with the north, particularly Wigan, Doncaster and Sunderland at the greatest risk from robots.

More than 100 of the world's leading experts in Artificial Intelligence (AI) and ethics have signed up to be part of a new journal created by a North East professor. University of Sunderland's Pro-Vice-Chancellor John MacIntyre launches'AI and Ethics' this month alongside his co-Editor-in-Chief, Professor Larry Medsker of George Washington University in the US, and Rachel Moriarty, Publishing Editor at Springer. Five years in the making, the journal has attracted around 100 of the world's leading thinkers and practitioners in this field of study to be part of its editorial board and aims to promote informed debate and discussion of the ethical, regulatory and policy implications that arise from the development of AI. Professor MacIntyre said: "Our objective is to be useful to a wide range of audiences – the academic and scientific community, the commercial and product development community, users of AI, those developing governance and regulatory frameworks for AI, and the public. We want to provide an outlet to publish high-quality work and making it available to be used by those audiences."