Entity matching, a core data integration problem, is the task of deciding whether two data tuples refer to the same real-world entity. Recent advances in deep learning methods, using pre-trained language models, were proposed for resolving entity matching. Although demonstrating unprecedented results, these solutions suffer from a major drawback as they require large amounts of labeled data for training, and, as such, are inadequate to be applied to low resource entity matching problems. To overcome the challenge of obtaining sufficient labeled data we offer a new active learning approach, focusing on a selection mechanism that exploits unique properties of entity matching. We argue that a distributed representation of a tuple pair indicates its informativeness when considered among other pairs. This is used consequently in our approach that iteratively utilizes space-aware considerations. Bringing it all together, we treat the low resource entity matching problem as a Battleship game, hunting indicative samples, focusing on positive ones, through awareness of the latent space along with careful planning of next sampling iterations. An extensive experimental analysis shows that the proposed algorithm outperforms state-of-the-art active learning solutions to low resource entity matching, and although using less samples, can be as successful as state-of-the-art fully trained known algorithms.

Social media play a significant role in shaping public opinion and influencing ideological communities through information propagation.

This report examines whether advanced AIs that perform well in training will be doing so in order to gain power later -- a behavior I call "scheming" (also sometimes called "deceptive alignment"). I conclude that scheming is a disturbingly plausible outcome of using baseline machine learning methods to train goal-directed AIs sophisticated enough to scheme (my subjective probability on such an outcome, given these conditions, is roughly 25%). In particular: if performing well in training is a good strategy for gaining power (as I think it might well be), then a very wide variety of goals would motivate scheming -- and hence, good training performance. This makes it plausible that training might either land on such a goal naturally and then reinforce it, or actively push a model's motivations towards such a goal as an easy way of improving performance. What's more, because schemers pretend to be aligned on tests designed to reveal their motivations, it may be quite difficult to tell whether this has occurred. However, I also think there are reasons for comfort. In particular: scheming may not actually be such a good strategy for gaining power; various selection pressures in training might work against schemer-like goals (for example, relative to non-schemers, schemers need to engage in extra instrumental reasoning, which might harm their training performance); and we may be able to increase such pressures intentionally. The report discusses these and a wide variety of other considerations in detail, and it suggests an array of empirical research directions for probing the topic further.

The prevalence of propaganda in our digital society poses a challenge to societal harmony and the dissemination of truth. Detecting propaganda through NLP in text is challenging due to subtle manipulation techniques and contextual dependencies. To address this issue, we investigate the effectiveness of modern Large Language Models (LLMs) such as GPT-3 and GPT-4 for propaganda detection. We conduct experiments using the SemEval-2020 task 11 dataset, which features news articles labeled with 14 propaganda techniques as a multi-label classification problem. Five variations of GPT-3 and GPT-4 are employed, incorporating various prompt engineering and fine-tuning strategies across the different models. We evaluate the models' performance by assessing metrics such as $F1$ score, $Precision$, and $Recall$, comparing the results with the current state-of-the-art approach using RoBERTa. Our findings demonstrate that GPT-4 achieves comparable results to the current state-of-the-art. Further, this study analyzes the potential and challenges of LLMs in complex tasks like propaganda detection.

Community detection and graph clustering are essential for unsupervised data exploration and understanding the high-level organisation of networked systems. Recently, graph clustering has received attention as a primary task for graph neural networks. Although hierarchical graph pooling has been shown to improve performance in graph and node classification tasks, it performs poorly in identifying meaningful clusters. Community detection has a long history in network science, but typically relies on optimising objective functions with custom-tailored search algorithms, not leveraging recent advances in deep learning, particularly from graph neural networks. In this paper, we narrow this gap between the deep learning and network science communities. We consider the map equation, an information-theoretic objective function for unsupervised community detection. Expressing it in a fully differentiable tensor form that produces soft cluster assignments, we optimise the map equation with deep learning through gradient descent. More specifically, the reformulated map equation is a loss function compatible with any graph neural network architecture, enabling flexible clustering and graph pooling that clusters both graph structure and data features in an end-to-end way, automatically finding an optimum number of clusters without explicit regularisation by following the minimum description length principle. We evaluate our approach experimentally using different neural network architectures for unsupervised clustering in synthetic and real data. Our results show that our approach achieves competitive performance against baselines, naturally detects overlapping communities, and avoids over-partitioning sparse graphs.

Unconditional scene inference and generation are challenging to learn jointly with a single compositional model. Despite encouraging progress on models that extract object-centric representations (''slots'') from images, unconditional generation of scenes from slots has received less attention. This is primarily because learning the multi-object relations necessary to imagine coherent scenes is difficult. We hypothesize that most existing slot-based models have a limited ability to learn object correlations. We propose two improvements that strengthen object correlation learning. The first is to condition the slots on a global, scene-level variable that captures higher-order correlations between slots. Second, we address the fundamental lack of a canonical order for objects in images by proposing to learn a consistent order to use for the autoregressive generation of scene objects. Specifically, we train an autoregressive slot prior to sequentially generate scene objects following a learned order. Ordered slot inference entails first estimating a randomly ordered set of slots using existing approaches for extracting slots from images, then aligning those slots to ordered slots generated autoregressively with the slot prior. Our experiments across three multi-object environments demonstrate clear gains in unconditional scene generation quality. Detailed ablation studies are also provided that validate the two proposed improvements.

In the 1983 movie WarGames, the US defence department runs a superintelligent central computer that is hacked into by a teenager, who unwittingly almost causes a nuclear Armageddon. The end of the world is averted when the computer, known as Joshua, learns, after playing tic-tac-toe with the teenager, that nuclear war cannot have a winner. The insight causes him to rescind missile launch orders with the comment: "A strange game. The only winning move is not to play." Joshua embodied the idea that a superintelligent AI would have an anthropomorphic mindset.

The artist is completely focused, a black oil crayon in her hand as she repeatedly draws a small circle on a vibrant teal canvas. She is unbothered by the three people closely observing her every movement, and doesn't seem to register my entrance into this bright white room inside the National Gallery of Victoria. The artist is a robot; more specifically, Basia is a 30kg "Spot" robot dog designed by Boston Dynamics. You've likely seen videos of these dogs opening doors, climbing stairs and decorating Christmas trees, while performing eerily fluid actions that cause people to write comments like, "Can't wait to have a pack of these chase me through a post-apocalyptic urban hellscape!" The robots are designed to perform tasks that are dangerous for humans: they tend to be bought by mining and construction corporations, as well as police and the military.

Russian air defences have intercepted Ukrainian drones over several regions inside its territory, including Moscow, just a day after Kyiv reported the "largest drone attack" on Ukraine since Moscow invaded the country in February last year. "Air defence destroyed four Ukrainian drones over the territory of the Bryansk, Smolensk and Tula regions," Russia's Ministry of Defence said in a statement on Sunday. Earlier, Russia said some drones were shot down over the Moscow region. The Russian army said it had also downed two Ukrainian missiles headed for Russia over the Sea of Azov, between the two countries. Ukraine, meanwhile, said its air defence had downed eight out of nine drones over the country on Sunday.

Carbon accounting is a fundamental building block in our global path to emissions reduction and decarbonization, yet many challenges exist in achieving reliable and trusted carbon accounting measures. We motivate that carbon accounting not only needs to be more data-driven, but also more methodologically sound. We discuss the need for alternative, more diverse data sources that can play a significant role on our path to trusted carbon accounting procedures and elaborate on not only why, but how Artificial Intelligence (AI) in general and Natural Language Processing (NLP) in particular can unlock reasonable access to a treasure trove of alternative data sets in light of the recent advances in the field that better enable the utilization of unstructured data in this process. We present a case study of the recent developments on real-world data via an NLP-powered analysis using OpenAI's GPT API on financial and shipping data. We conclude the paper with a discussion on how these methods and approaches can be integrated into a broader framework for AI-enabled integrative carbon accounting.