In response to the increasing use of interactive artificial intelligence, the demand for the capacity to handle complex questions has increased. Multi-hop question generation aims to generate complex questions that requires multi-step reasoning over several documents. Previous studies have predominantly utilized end-to-end models, wherein questions are decoded based on the representation of context documents. However, these approaches lack the ability to explain the reasoning process behind the generated multi-hop questions. Additionally, the question rewriting approach, which incrementally increases the question complexity, also has limitations due to the requirement of labeling data for intermediate-stage questions. In this paper, we introduce an end-to-end question rewriting model that increases question complexity through sequential rewriting. The proposed model has the advantage of training with only the final multi-hop questions, without intermediate questions. Experimental results demonstrate the effectiveness of our model in generating complex questions, particularly 3- and 4-hop questions, which are appropriately paired with input answers. We also prove that our model logically and incrementally increases the complexity of questions, and the generated multi-hop questions are also beneficial for training question answering models.

Hypergraphs are marked by complex topology, expressing higher-order interactions among multiple nodes with hyperedges, and better capturing the topology is essential for effective representation learning. Recent advances in generative self-supervised learning (SSL) suggest that hypergraph neural networks learned from generative self supervision have the potential to effectively encode the complex hypergraph topology. Designing a generative SSL strategy for hypergraphs, however, is not straightforward. Questions remain with regard to its generative SSL task, connection to downstream tasks, and empirical properties of learned representations. In light of the promises and challenges, we propose a novel generative SSL strategy for hypergraphs. We first formulate a generative SSL task on hypergraphs, hyperedge filling, and highlight its theoretical connection to node classification. Based on the generative SSL task, we propose a hypergraph SSL method, HypeBoy. HypeBoy learns effective general-purpose hypergraph representations, outperforming 16 baseline methods across 11 benchmark datasets.

We present a mathematical framework for modeling two-player noncooperative games in which one player (the defender) is uncertain of the costs of the game and the second player's (the attacker's) intention but can preemptively allocate information-gathering resources to reduce this uncertainty. We obtain the defender's decisions by solving a two-stage problem. In Stage 1, the defender allocates information-gathering resources, and in Stage 2, the information-gathering resources output a signal that informs the defender about the costs of the game and the attacker's intent, and then both players play a noncooperative game. We provide a gradient-based algorithm to solve the two-stage game and apply this framework to a tower-defense game which can be interpreted as a variant of a Colonel Blotto game with smooth payoff functions and uncertainty over battlefield valuations. Finally, we analyze how optimal decisions shift with changes in information-gathering allocations and perturbations in the cost functions.

An AI chatbot released by the New York City government to help business owners access pertinent information has been spouting falsehoods, at times even misinforming users about actions that are against the law, according to a report from The Markup. The report, which was co-published with the local nonprofit newsrooms Documented and The City, includes numerous examples of inaccuracies in the chatbot's responses to questions relating to housing policies, workers' rights and other topics. Mayor Adams' administration introduced the chatbot in October as an addition to the MyCity portal, which launched in March 2023 as "a one-stop shop for city services and benefits." The chatbot, powered by Microsoft's Azure AI, is aimed at current and aspiring business owners, and was billed as a source of "actionable and trusted information" that comes directly from the city government's sites. But it is a pilot program, and a disclaimer on the website notes that it "may occasionally produce incorrect, harmful or biased content."

Voice synthesis has come a long way since 1978's Speak & Spell toy, which once wowed people with its state-of-the-art ability to read words aloud using an electronic voice. Now, using deep-learning AI models, software can create not only realistic-sounding voices but can also convincingly imitate existing voices using small samples of audio. Along those lines, OpenAI this week announced Voice Engine, a text-to-speech AI model for creating synthetic voices based on a 15-second segment of recorded audio. It has provided audio samples of the Voice Engine in action on its website. This story originally appeared on Ars Technica, a trusted source for technology news, tech policy analysis, reviews, and more.

If humanity is obliterated by climate change, how will we even know it's happened? That's the question being answered by Australian scientists, who are building Earth's Black Box – a 32-foot-long steel monolith that captures data about our planet. It'll be filled with hard drives that constantly document climate change, giving an'unbiased account of events' that lead to Earth's demise. In the event of a climate apocalypse, it will provide a document of how humanity failed to avoid the disaster – as long as there's someone or something around to access it. Artist impressions suggest it will have a similar aura to the mysterious monolith in Stanley Kubrick's sci-fi film '2001: A Space Odyssey'.

At least one person has been killed and two were injured after a drone crashed into an apartment building in Russia's Belgorod region. Authorities there said they evacuated more than 3,500 children following a spate of Ukrainian attacks. Russia targeted Ukraine's key energy infrastructure in escalated shelling, firing dozens of drones and missiles and injuring at least six people, according to Ukrainian officials. Ukraine's Air Force said 99 missiles and drones were fired, but 84 of them were intercepted. Ukraine introduced emergency blackouts in three regions – Dnipropetrovsk, Zaporizhia and Kirovograd – because of the attacks, and the authorities urged consumers in other regions to limit electricity consumption.

The publication said it obtained a memo from House Chief Administrative Officer Catherine Szpindor, telling Congress personnel that the AI chatbot is now officially prohibited. Apparently, the Office of Cybersecurity has deemed Copilot to be a risk "due to the threat of leaking House data to non-House approved cloud services." While there's nothing stopping them from using Copilot on their own phones and laptops, it will now be blocked on all Windows devices owned by the Congress. Almost a year ago, the Congress also set a strict limit on the use of ChatGPT, which is powered by OpenAI's large language models, just like Copilot. It banned staffers from using the chatbot's free version on House computers, but it allowed them to continue using the paid (ChatGPT Plus) version for research and evaluation due to its tighter privacy controls.

Increasingly, more software services have been published onto the Internet, making it a big challenge to recommend services in the process of a scientific workflow composition. In this paper, a novel context-aware approach is proposed to recommending next services in a workflow development process, through learning service representation and service selection decision making behaviors from workflow provenance. Inspired by natural language sentence generation, the composition process of a scientific workflow is formalized as a step-wise procedure within the context of the goal of workflow, and the problem of next service recommendation is mapped to next word prediction. Historical service dependencies are first extracted from scientific workflow provenance to build a knowledge graph. Service sequences are then generated based on diverse composition path generation strategies. Afterwards, the generated corpus of composition paths are leveraged to study previous decision making strategies. Such a trained goal-oriented next service prediction model will be used to recommend top K candidate services during workflow composition process. Extensive experiments on a real-word repository have demonstrated the effectiveness of this approach.

Reliable detection, localization and identification of small drones is essential to promote safe, secure and privacy-respecting operation of Unmanned-Aerial Systems (UAS), or simply, drones. This is an increasingly challenging problem with only single modality sensing, especially, to detect and identify small drones. In this work, a multi-stage fusion architecture using passive radio frequency (RF) and electro-optic (EO) imagery data is developed to leverage the synergies of the modalities to improve the overall tracking and classification capabilities. For detection with EO-imagery, supervised deep learning based techniques as well as unsupervised foreground/background separation techniques are explored to cope with challenging environments. Using real collected data for Group 1 and 2 drones, the capability of each algorithm is quantified. In order to compensate for any performance gaps in detection with only EO imagery as well as to provide a unique device identifier for the drones, passive RF is integrated with EO imagery whenever available. In particular, drone detections in the image plane are combined with passive RF location estimates via detection-to-detection association after 3D to 2D transformation. Final tracking is performed on the composite detections in the 2D image plane. Each track centroid is given a unique identification obtained via RF fingerprinting. The proposed fusion architecture is tested and the tracking and performance is quantified over the range to illustrate the effectiveness of the proposed approaches using simultaneously collected passive RF and EO data at the Air Force Research Laboratory (AFRL) through ESCAPE-21 (Experiments, Scenarios, Concept of Operations, and Prototype Engineering) data collect