We train a language model (LM) to robustly answer multistep questions by generating and answering sub-questions. We propose Chain-of-Questions, a framework that trains a model to generate sub-questions and sub-answers one at a time by leveraging human annotated question decomposition meaning representation (QDMR). The key technical challenge is that QDMR only contains sub-questions but not answers to those sub-questions, so we treat sub-answers as latent variables and optimize them using a novel dynamic mixture of Hard-EM and MAPO. Chain-of-Questions greatly outperforms strong neuro-symbolic methods by 9.0 F1 on DROP contrast set, and outperforms GPT-3.5 by 24.3 F1 on HOTPOTQA adversarial set, thus demonstrating the effectiveness and robustness of our framework.

While network coverage maps continue to expand, many devices located in remote areas remain unconnected to terrestrial communication infrastructures, preventing them from getting access to the associated data-driven services. In this paper, we propose a ground-to-satellite cooperative federated learning (FL) methodology to facilitate machine learning service management over remote regions. Our methodology orchestrates satellite constellations to provide the following key functions during FL: (i) processing data offloaded from ground devices, (ii) aggregating models within device clusters, and (iii) relaying models/data to other satellites via inter-satellite links (ISLs). Due to the limited coverage time of each satellite over a particular remote area, we facilitate satellite transmission of trained models and acquired data to neighboring satellites via ISL, so that the incoming satellite can continue conducting FL for the region. We theoretically analyze the convergence behavior of our algorithm, and develop a training latency minimizer which optimizes over satellite-specific network resources, including the amount of data to be offloaded from ground devices to satellites and satellites' computation speeds. Through experiments on three datasets, we show that our methodology can significantly speed up the convergence of FL compared with terrestrial-only and other satellite baseline approaches.

In district-based multi-party elections, electors cast votes in their respective districts. In each district, the party with maximum votes wins the corresponding seat in the governing body. Election Surveys try to predict the election outcome (vote shares and seat shares of parties) by querying a random sample of electors. However, the survey results are often inconsistent with the actual results, which could be due to multiple reasons. The aim of this work is to estimate a posterior distribution over the possible outcomes of the election, given one or more survey results. This is achieved using a prior distribution over vote shares, election models to simulate the complete election from the vote share, and survey models to simulate survey results from a complete election. The desired posterior distribution over the space of possible outcomes is constructed using Synthetic Dirichlet Likelihoods, whose parameters are estimated from Monte Carlo sampling of elections using the election models. We further show the same approach can also use be used to evaluate the surveys - whether they were biased or not, based on the true outcome once it is known. Our work offers the first-ever probabilistic model to analyze district-based election surveys. We illustrate our approach with extensive experiments on real and simulated data of district-based political elections in India.

Let us be thankful for the AI industry. Its leaders may be nudging humans closer to extinction, but this year, they provided us with a gloriously messy spectacle of progress. When I say "year," I mean the long year that began late last November, when OpenAI released ChatGPT and, in doing so, launched generative AI into the cultural mainstream. In the months that followed, politicians, teachers, Hollywood screenwriters, and just about everyone else tried to understand what this means for their future. Cash fire-hosed into AI companies, and their executives, now glowed up into international celebrities, fell into Succession-style infighting.

Russia has warned that it will react robustly to Western moves to seize its assets or deploy missiles. Moscow could sever diplomatic relations with the United States should it confiscate Russian assets frozen under sanctions, Deputy Foreign Minister Sergey Ryabkov said on Friday. Officials also said the Kremlin would respond to the deployment of missiles in Europe or Asia, even as Ukraine reported that Russia had unleashed another barrage of attack drones overnight. Ryabkov threatened that Moscow could cut diplomatic ties with Washington should it hand frozen Russian assets to Kyiv, which is desperate for funds, according to the Russian state news agency Interfax. Western countries are discussing the confiscation of more than $1bn in Russian assets frozen due to sanctions over the war in Ukraine.

As autonomous systems increasingly become part of our lives, it is crucial to foster trust between humans and these systems, to ensure positive outcomes and mitigate harmful ones.

Smart medical gadgets are crucial for keeping people alive and healthy. From wearables that keep an eye on your heart rate all day to heart pumps and big machines such as ventilators and dialysis units, these devices often work non-stop. However, the sad reality is that cyber-security is not always top of mind when these devices are being created. Many are easily connected to the Internet, often have simple passwords, or sometimes do not even require passwords. This lack of security is a huge problem because it allows hackers to not only break into the devices themselves, but also to penetrate hospital systems and wreak havoc with harmful software.

During the first six weeks of the war in Gaza, Israel routinely used one of its biggest and most destructive bombs in areas it designated safe for civilians, according to an analysis of visual evidence by The New York Times. The video investigation focuses on the use of 2,000-pound bombs in an area of southern Gaza where Israel had ordered civilians to move for safety. While bombs of that size are used by several Western militaries, munitions experts say they are almost never dropped by U.S. forces in densely populated areas anymore. The Times programmed an artificial intelligence tool to scan satellite imagery of south Gaza for bomb craters. Times reporters manually reviewed the search results, looking for craters measuring roughly 40 feet across or larger.

The Immigration Services Agency said Friday that it will grant long-term residency to fourth-generation foreigners of Japanese descent from countries such as Brazil and Peru. It will revise the residency status system to allow such people to effectively stay in Japan indefinitely, if they meet requirements such as having lived in Japan for at least five years and having a certain level of Japanese-language proficiency. The revision, aimed at attracting such people to Japan amid labor shortages due to a decreasing population, will be implemented as early as Thursday. "We'll ease the requirements so that more people can come to Japan," Justice Minister Ryuji Koizumi told a news conference. The current system for fourth-generation descendants was introduced in 2018 so that such people can study the Japanese language and culture while working.

In recent years, there has been a revolution in data-driven policing. With that has come scrutiny on how bias in historical data affects algorithmic decision making. In this exploratory work, we introduce a debiasing technique for place-based algorithmic patrol management systems. We show that the technique efficiently eliminates racially biased features while retaining high accuracy in the models. Finally, we provide a lengthy list of potential future research in the realm of fairness and data-driven policing which this work uncovered.