How can we effectively and efficiently learn node representations in signed bipartite graphs? A signed bipartite graph is a graph consisting of two nodes sets where nodes of different types are positively or negative connected, and it has been extensively used to model various real-world relationships such as e-commerce, etc. To analyze such a graph, previous studies have focused on designing methods for learning node representations using graph neural networks. In particular, these methods insert edges between nodes of the same type based on balance theory, enabling them to leverage augmented structures in their learning. However, the existing methods rely on a naive message passing design, which is prone to over-smoothing and susceptible to noisy interactions in real-world graphs. Furthermore, they suffer from computational inefficiency due to their heavy design and the significant increase in the number of added edges. In this paper, we propose ELISE, an effective and lightweight GNN-based approach for learning signed bipartite graphs. We first extend personalized propagation to a signed bipartite graph, incorporating signed edges during message passing. This extension adheres to balance theory without introducing additional edges, mitigating the over-smoothing issue and enhancing representation power. We then jointly learn node embeddings on a low-rank approximation of the signed bipartite graph, which reduces potential noise and emphasizes its global structure, further improving expressiveness without significant loss of efficiency. We encapsulate these ideas into ELISE, designing it to be lightweight, unlike the previous methods that add too many edges and cause inefficiency. Through extensive experiments on real-world signed bipartite graphs, we demonstrate that ELISE outperforms its competitors for predicting link signs while providing faster training and inference time.

We consider the problem of red teaming LLMs on elementary calculations and algebraic tasks to evaluate how various prompting techniques affect the quality of outputs. We present a framework to procedurally generate numerical questions and puzzles, and compare the results with and without the application of several red teaming techniques. Our findings suggest that even though structured reasoning and providing worked-out examples slow down the deterioration of the quality of answers, the gpt-3.5-turbo and gpt-4 models are not well suited for elementary calculations and reasoning tasks, also when being red teamed.

Large Language Models (LLMs) have shown remarkable capabilities in general natural language processing tasks but often fall short in complex reasoning tasks. Recent studies have explored human-like problem-solving strategies, such as self-correct, to push further the boundary of single-model reasoning ability. In this work, we let a single model "step outside the box" by engaging multiple models to correct each other. We introduce a multi-agent collaboration strategy that emulates the academic peer review process. Each agent independently constructs its own solution, provides reviews on the solutions of others, and assigns confidence levels to its reviews. Upon receiving peer reviews, agents revise their initial solutions. Extensive experiments on three different types of reasoning tasks show that our collaboration approach delivers superior accuracy across all ten datasets compared to existing methods. Further study underscores the effectiveness of integrating confidence in reviews, demonstrates the superiority of feedback exchange over mere solution sharing, and highlights the role of capability and diversity in fostering successful collaboration.

The European Vision for AI event, held on 22 April 2021, provided an opportunity for the public to hear from members of the European artificial intelligence (AI) community and representatives from the European Commission and parliament. The morning-long session was organised by the VISION project partners in cooperation with four networks of AI centres of excellence (AI4Media, ELISE, TAILOR, Humane-AI-Net). These networks were launched within the European Union's Horizon 2020 Programme in September 2020 and are bringing together scientists across Europe. This event followed hot on the heels of the announcement from the European Commission regarding proposed new rules and actions for artificial intelligence. During the morning, the speakers provided some context and details around this and there was plenty of interesting discussion on potential paths forward for AI in Europe.

You play as Templars (the antagonists of the series) who are training by using the Animus, learning how to hunt and kill assassins, which is a neat twist. It's a game of cat and mouse: you're given a target to track and kill while other players are hunt you as well. The premise is so unique, and so satisfyingly tense. I can't think of any other multiplayer experience that put so many resources into building a compelling stealth experience to play with friends. I loved being able to sneak up to a target and poison them silently, then watch them collapse like a rag doll moments later.