Long-context models (LCMs) have made remarkable strides in recent years, offering users great convenience for handling tasks that involve long context, such as document summarization. As the community increasingly prioritizes the faithfulness of generated results, merely ensuring the accuracy of LCM outputs is insufficient, as it is quite challenging for humans to verify the results from the extremely lengthy context. Yet, although some efforts have been made to assess whether LCMs respond truly based on the context, these works either are limited to specific tasks or heavily rely on external evaluation resources like GPT4.In this work, we introduce L-CiteEval, a comprehensive multi-task benchmark for long-context understanding with citations, aiming to evaluate both the understanding capability and faithfulness of LCMs. L-CiteEval covers 11 tasks from diverse domains, spanning context lengths from 8K to 48K, and provides a fully automated evaluation suite. Through testing with 11 cutting-edge closed-source and open-source LCMs, we find that although these models show minor differences in their generated results, open-source models substantially trail behind their closed-source counterparts in terms of citation accuracy and recall. This suggests that current open-source LCMs are prone to responding based on their inherent knowledge rather than the given context, posing a significant risk to the user experience in practical applications. We also evaluate the RAG approach and observe that RAG can significantly improve the faithfulness of LCMs, albeit with a slight decrease in the generation quality. Furthermore, we discover a correlation between the attention mechanisms of LCMs and the citation generation process.

Getting on an airplane should be the start of a relaxing trip to another location. But nothing triggers panic quite so much as seeing your baggage precariously balancing on towing vehicles from outside the plane window prior to departure. Thankfully, these human-driven baggage tow'tractors' could soon be a thing of the past. British Airways is to start using a self-driving baggage robot called'Auto-DollyTug' at Gatwick Airport later this year. The machines will pick up suitcases from the terminal building and ferry them across the tarmac in closed containers to awaiting aircraft.

England is famous for its eccentric place names, from'Matching Tye' to'Fingringhoe' and'Upton Snodsbury'. But a new AI study now reveals the most English-sounding locations in the country – and they certainly conjure up images of cricket and afternoon tea. The study shows that'Harlington', a district of London, is the most archetypal English place name, along with'Widdington' in Essex and'Colworth' in West Sussex. It contrast, 'Anna', a settlement in Hampshire, is the least English-sounding, along with'Belgravia' in London and'Moira' in Leicestershire. Although AI was used to determine the language basis of English place names, not the meaning, the results could reveal more about the history of the locations.

A motorist who received a fine after driving through Gatwick Airport's drop-off area challenged it using ChatGPT artificial intelligence (AI) and won a much-reduced penalty. Shaun Bosley, from Brighton, was dropping a work colleague at the airport last November and received a £100 "final notice" from NCP several months later, despite saying he had received no previous correspondence. Mr Bosley, a sales consultant for Phyron, a Swedish company which produces videos for car dealerships using AI, turned to ChatGPT, which generates human-like conversations. Users simply type a request into a chat box and the system can generate a response almost instantly. I didn't have to look at it and think'that sounds like a robot, I need to change some of it' "In the end, I just typed, 'write an appeal to a penalty charge notice for driving through Gatwick airport. I have received final notice, but never received first notice of the penalty', and straight away it came back with a great response," he told the PA news agency.

The Royal Surrey Foundation Trust treated Emma McCormick, 44, using adaptive radiotherapy after she was diagnosed with the cancer last April and was referred to St Luke's Cancer Centre. The treatment, called Ethos, involves a machine, created by healthcare company Varian, which uses artificial intelligence to deliver a prescription dose to tumours. The AI technology uses daily CT scans to target the specific areas that need radiotherapy, which helps avoid damage to healthy tissue and limit side-effects. Patients are required only to lay still on a flat surface inside the machine for the duration of the treatment. There is a screen above the machine which shows different images, and medical staff can play music to make the treatment more comfortable.

"By understanding how people enjoy the Space Needle's observation decks, food and beverage experiences, and amenities, we can better provide both a safe and enjoyable experience," said Luis Quintero, senior operations manager at the Space Needle. "Through Veovo's crowd management solution, we can reduce and prevent overcrowding, while understanding trends over time will allow us to optimise our operations and resourcing." London Gatwick Airport will use Passenger Predictability solution to optimise security operations and improve passenger flow. The partnership will allow the airport to efficiently handle increasing passenger numbers and build back better for a more sustainable, passenger-centred travel experience. The AI-powered technology gives Gatwick real-time awareness of people's movement and experiences in the North and South terminal security areas.

The Kuhl's pipistrelle bat is native to the Mediterranean region, with only a handful of records in Britain. However, a bat detector set up in a private garden in West Sussex caught and logged over 50 audio recordings containing the social calls of this species. The bat detector was running as part of the Chichester Bat Recording Project, and the audio was uploaded to the BTO's Acoustic Pipeline along with the other recordings from the project. The Acoustic Pipeline automatically identified that these social calls were being emitted by a Kuhl's pipestrelle and flagged the recordings as being special and unusual for that location. "We started using the bat detector four years ago, leaving it overnight in the gardens of Society members and their friends and have been amazed by the number of bat records at every garden," say Ken and Linda Smith, co-ordinators of the bat recording project for Chichester Natural History Society.

The first flight took place at a secret test location in the South Australian desert, while three remotely-piloted Grands Prix are planned across the world this year in Airspeeder's electric racing series.

Entity set expansion and synonym discovery are two critical NLP tasks. Previous studies accomplish them separately, without exploring their interdependencies. In this work, we hypothesize that these two tasks are tightly coupled because two synonymous entities tend to have similar likelihoods of belonging to various semantic classes. This motivates us to design SynSetExpan, a novel framework that enables two tasks to mutually enhance each other. SynSetExpan uses a synonym discovery model to include popular entities' infrequent synonyms into the set, which boosts the set expansion recall. Meanwhile, the set expansion model, being able to determine whether an entity belongs to a semantic class, can generate pseudo training data to fine-tune the synonym discovery model towards better accuracy. To facilitate the research on studying the interplays of these two tasks, we create the first large-scale Synonym-Enhanced Set Expansion (SE2) dataset via crowdsourcing. Extensive experiments on the SE2 dataset and previous benchmarks demonstrate the effectiveness of SynSetExpan for both entity set expansion and synonym discovery tasks.

Scientists have built an AI tool that finds drone pilots flying dangerously close to airports or protected airspace. The system aims to reduce the risks drones pose to aircraft. Not only can they collide with planes, but they can also interfere with radio signals, causing a pilot to lose control of the aircraft. These risks have already caused chaos at a number of airports. Most notoriously, London's Gatwick airport was forced to shut down in December 2018 after drones were spotted near the runway.