Hundreds of passengers flying to Dubai spent 11 hours on a flight to nowhere after their plane was turned back over Egypt. The Emirates flight EK24 set off from Edinburgh at 21:26 on Sunday and was due to land in Dubai at 06:49 on Monday. However, as the plane flew over Egypt, flights at Dubai International Airport were suspended following a fire caused by an Iranian drone hitting a fuel tank. The plane was forced to return to Edinburgh. Travel journalist Simon Calder told the BBC's Radio Scotland Breakfast programme that although Dubai was on the UK Foreign Office's No go list, many people were still taking the risk of flying there. No injuries were reported following the drone strike but officials said they had taken all necessary measures to ensure public safety.

LLMs are remarkable artifacts that have revolutionized a range of NLP and AI tasks. A significant contributor is their factual knowledge, which, to date, remains poorly understood, and is usually analyzed from biased samples. In this paper, we take a deep tour into the factual knowledge (or beliefs) of a frontier LLM, based on GPTKB v1.5 (Hu et al., 2025a), a recursively elicited set of 100 million beliefs of one of the strongest currently available frontier LLMs, GPT-4.1. We find that the models' factual knowledge differs quite significantly from established knowledge bases, and that its accuracy is significantly lower than indicated by previous benchmarks. We also find that inconsistency, ambiguity and hallucinations are major issues, shedding light on future research opportunities concerning factual LLM knowledge.

China's first three-on-three robot football tournament kicked off in Beijing last Sunday. But the quality of play on show suggests that a robot won't be claiming the Ballon d'Or any time soon. As the AI-controlled bots shuffled slowly across the turf, they bumped into each other, toppled over, and only occasionally even kicked the ball. By the time the final whistle blew, two bots had to be stretchered off the pitch after taking falls that would earn most human players a yellow card for diving. Cheng Hao, founder of Booster Robotics, which supplied the robots for the tournament, told the Global Times that the robots currently have the skills of five-to six-year-old children.

From Kevin Keegan to David Beckham and Michael Owen, many prolific footballers have won themselves simple-minded reputations as well as trophies. But scientists say elite football stars are actually'super-clever individuals'. 'Footballers often do not pursue higher education, such as university degrees, because their focus and interests lie elsewhere – primarily in their sport,' Professor Leonardo Bonetti, study author at Aarhus University in Denmark, told MailOnline. 'While this may mean they are less knowledgeable in certain academic areas, it does not reflect a lack of intelligence. 'Unfortunately, people often confuse being less formally educated with being less clever, which perpetuates this unfair stereotype.' Famously, former striker and England manager Keegan once said of Argentina: 'They're the second-best team in the world, and there's no higher praise than that.' Meanwhile, Beckham memorably commented after the birth of his eldest son: 'I want Brooklyn to be christened, but I don't know into what religion.'

Football coaches desperate to boost their team's performance could soon find an answer in an artificial intelligence system aimed at conjuring the next superstar. A kind of sporting Aladdin's lamp is within reach, technologists claim, which could allow managers to simply wish for a new player with the aggression of Erling Haaland or the poise of Jude Bellingham and for an AI to suggest the perfect prospect. A system that uses video and automated tracking to monitor the performances of nearly 180,000 mostly teenage footballers around the world underpins the services of Eyeball, a digital scouting company that already has relationships with more than a dozen Premier League clubs and other elite teams in Europe and North America. Using what it claims is the largest video database of global youth football – with players logged from 28 countries – the company says it can now determine which young players most fit the description of current or recent top stars as defined by one of eight archetypes. The characteristics of the ideal midfielder are a blend of Steven Gerrard, Kevin De Bruyne, Dominik Szoboszlai, Federico Valverde, Dani Olmo and Bellingham – all top-ranked internationals.

Large Language Models (LLMs) are limited by their parametric knowledge, leading to hallucinations in knowledge-extensive tasks. To address this, Retrieval-Augmented Generation (RAG) incorporates external document chunks to expand LLM knowledge. Furthermore, compressing information from document chunks through extraction or summarization can improve LLM performance. Nonetheless, LLMs still struggle to notice and utilize scattered key information, a problem known as the "lost-in-the-middle" syndrome. Therefore, we typically need to restructure the content for LLM to recognize the key information. We propose $\textit{Refiner}$, an end-to-end extract-and-restructure paradigm that operates in the post-retrieval process of RAG. $\textit{Refiner}$ leverages a single decoder-only LLM to adaptively extract query-relevant contents verbatim along with the necessary context, and section them based on their interconnectedness, thereby highlights information distinction, and aligns downstream LLMs with the original context effectively. Experiments show that a trained $\textit{Refiner}$ (with 7B parameters) exhibits significant gain to downstream LLM in improving answer accuracy, and outperforms other state-of-the-art advanced RAG and concurrent compressing approaches in various single-hop and multi-hop QA tasks. Notably, $\textit{Refiner}$ achieves a 80.5% tokens reduction and a 1.6-7.0% improvement margin in multi-hop tasks compared to the next best solution. $\textit{Refiner}$ is a plug-and-play solution that can be seamlessly integrated with RAG systems, facilitating its application across diverse open-source frameworks.

We developed an artificial intelligence approach to predict the transfer fee of a football player. This model can help clubs make better decisions about which players to buy and sell, which can lead to improved performance and increased club budgets. Having collected data on player performance, transfer fees, and other factors that might affect a player's value, we then used this data to train a machine learning model that can accurately predict a player's impact on the game. We further passed the obtained results as one of the features to the predictor of transfer fees. The model can help clubs identify players who are undervalued and who could be sold for a profit. It can also help clubs avoid overpaying for players. We believe that our model can be a valuable tool for football clubs. It can help them make better decisions about player recruitment and transfers.

Large Language Models (LLMs) are notorious for blending fact with fiction and generating non-factual content, known as hallucinations. To tackle this challenge, we propose an interactive system that helps users obtain insights into the reliability of the generated text. Our approach is based on the idea that the self-consistency of multiple samples generated by the same LLM relates to its confidence in individual claims in the generated texts. Using this idea, we design RELIC, an interactive system that enables users to investigate and verify semantic-level variations in multiple long-form responses. This allows users to recognize potentially inaccurate information in the generated text and make necessary corrections. From a user study with ten participants, we demonstrate that our approach helps users better verify the reliability of the generated text. We further summarize the design implications and lessons learned from this research for inspiring future studies on reliable human-LLM interactions.

United have won nine of their 10 matches in all competitions in the 22-year-old's absence, with Sancho currently following an individual training programme devised to get him back to the level required to play in the Premier League.