Recent developments in Large Language Models (LLMs) have significantly expanded their applications across various domains. However, the effectiveness of LLMs is often constrained when operating individually in complex environments. This paper introduces a transformative approach by organizing LLMs into community-based structures, aimed at enhancing their collective intelligence and problem-solving capabilities. We investigate different organizational models-hierarchical, flat, dynamic, and federated-each presenting unique benefits and challenges for collaborative AI systems. Within these structured communities, LLMs are designed to specialize in distinct cognitive tasks, employ advanced interaction mechanisms such as direct communication, voting systems, and market-based approaches, and dynamically adjust their governance structures to meet changing demands. The implementation of such communities holds substantial promise for improve problem-solving capabilities in AI, prompting an in-depth examination of their ethical considerations, management strategies, and scalability potential. This position paper seeks to lay the groundwork for future research, advocating a paradigm shift from isolated to synergistic operational frameworks in AI research and application.

This paper shows how to construct genre patterns, whose purpose is to guide interactive story composition in a way that enforces thematic consistency. To start the discussion we argue, based on previous seminal works, for the existence of five fundamental genres, namely comedy, romance - in the sense of epic plots, flourishing since the twelfth century -, tragedy, satire, and mystery. To construct the patterns, a simple two-phase process is employed: first retrieving examples that match our genre characterizations, and then applying a form of most specific generalization to the groups of examples in order to find their commonalities. In both phases, AI agents are instrumental, with our PatternTeller prototype being called to operate the story composition process, offering the opportunity to generate stories from a given premise of the user, to be developed under the guidance of the chosen pattern and trying to accommodate the user's suggestions along the composition stages.

With the impressive performance in various downstream tasks, large language models (LLMs) have been widely integrated into production pipelines, like recruitment and recommendation systems. A known issue of models trained on natural language data is the presence of human biases, which can impact the fairness of the system. This paper investigates LLMs' behavior with respect to gender stereotypes, in the context of occupation decision making. Our framework is designed to investigate and quantify the presence of gender stereotypes in LLMs' behavior via multi-round question answering. Inspired by prior works, we construct a dataset by leveraging a standard occupation classification knowledge base released by authoritative agencies. We tested three LLMs (RoBERTa-large, GPT-3.5-turbo, and Llama2-70b-chat) and found that all models exhibit gender stereotypes analogous to human biases, but with different preferences. The distinct preferences of GPT-3.5-turbo and Llama2-70b-chat may imply the current alignment methods are insufficient for debiasing and could introduce new biases contradicting the traditional gender stereotypes.

This paper introduces RoboCar, an open-source research platform for autonomous driving developed at the University of Luxembourg. RoboCar provides a modular, cost-effective framework for the development of experimental Autonomous Driving Systems (ADS), utilizing the 2018 KIA Soul EV. The platform integrates a robust hardware and software architecture that aligns with the vehicle's existing systems, minimizing the need for extensive modifications. It supports various autonomous driving functions and has undergone real-world testing on public roads in Luxembourg City. This paper outlines the platform's architecture, integration challenges, and initial test results, offering insights into its application in advancing autonomous driving research. RoboCar is available to anyone at https://github.com/sntubix/robocar and is released under an open-source MIT license.

Deep learning has shown incredible potential across a vast array of tasks and accompanying this growth has been an insatiable appetite for data. However, a large amount of data needed for enabling deep learning is stored on personal devices and recent concerns on privacy have further highlighted challenges for accessing such data. As a result, federated learning (FL) has emerged as an important privacy-preserving technology enabling collaborative training of machine learning models without the need to send the raw, potentially sensitive, data to a central server. However, the fundamental premise that sending model updates to a server is privacy-preserving only holds if the updates cannot be "reverse engineered" to infer information about the private training data. It has been shown under a wide variety of settings that this premise for privacy does {\em not} hold. In this survey paper, we provide a comprehensive literature review of the different privacy attacks and defense methods in FL. We identify the current limitations of these attacks and highlight the settings in which FL client privacy can be broken. We dissect some of the successful industry applications of FL and draw lessons for future successful adoption. We survey the emerging landscape of privacy regulation for FL. We conclude with future directions for taking FL toward the cherished goal of generating accurate models while preserving the privacy of the data from its participants.

The rapid advancements in large language models (LLMs) have opened new avenues across various fields, including cybersecurity, which faces an ever-evolving threat landscape and need for innovative technologies. Despite initial explorations into the application of LLMs in cybersecurity, there is a lack of a comprehensive overview of this research area. This paper bridge this gap by providing a systematic literature review, encompassing an analysis of over 180 works, spanning across 25 LLMs and more than 10 downstream scenarios. Our comprehensive overview addresses three critical research questions: the construction of cybersecurity-oriented LLMs, LLMs' applications in various cybersecurity tasks, and the existing challenges and further research in this area. This study aims to shed light on the extensive potential of LLMs in enhancing cybersecurity practices, and serve as a valuable resource for applying LLMs in this doamin. We also maintain and regularly updated list of practical guides on LLMs for cybersecurity at https://github.com/tmylla/Awesome-LLM4Cybersecurity.

As the last critical stage of RSs, Multi-Task Fusion (MTF) is responsible for combining multiple scores outputted by Multi-Task Learning (MTL) into a final score to maximize user satisfaction, which determines the ultimate recommendation results. Recently, to optimize long-term user satisfaction within a recommendation session, Reinforcement Learning (RL) is used for MTF in the industry. However, the off-policy RL algorithms used for MTF so far have the following severe problems: 1) to avoid out-of-distribution (OOD) problem, their constraints are overly strict, which seriously damage their performance; 2) they are unaware of the exploration policy used for producing training data and never interact with real environment, so only suboptimal policy can be learned; 3) the traditional exploration policies are inefficient and hurt user experience. To solve the above problems, we propose a novel method named IntegratedRL-MTF customized for MTF in large-scale RSs. IntegratedRL-MTF integrates off-policy RL model with our online exploration policy to relax overstrict and complicated constraints, which significantly improves its performance. We also design an extremely efficient exploration policy, which eliminates low-value exploration space and focuses on exploring potential high-value state-action pairs. Moreover, we adopt progressive training mode to further enhance our model's performance with the help of our exploration policy. We conduct extensive offline and online experiments in the short video channel of Tencent News. The results demonstrate that our model outperforms other models remarkably. IntegratedRL-MTF has been fully deployed in our RS and other large-scale RSs in Tencent, which have achieved significant improvements.

The ability to detect when a system undergoes an incipient fault is of paramount importance in preventing a critical failure. In this work, we propose an information-driven fault detection method based on a novel concept drift detector. The method is tailored to identifying drifts in input-output relationships of additive noise models (i.e., model drifts) and is based on a distribution-free mutual information (MI) estimator. Our scheme does not require prior faulty examples and can be applied distribution-free over a large class of system models. Our core contributions are twofold. First, we demonstrate the connection between fault detection, model drift detection, and testing independence between two random variables. Second, we prove several theoretical properties of the proposed MI-based fault detection scheme: (i) strong consistency, (ii) exponentially fast detection of the non-faulty case, and (iii) control of both significance levels and power of the test. To conclude, we validate our theory with synthetic data and the benchmark dataset N-CMAPSS of aircraft turbofan engines. These empirical results support the usefulness of our methodology in many practical and realistic settings, and the theoretical results show performance guarantees that other methods cannot offer.

Every publicly traded company in the US is required to file an annual 10-K financial report, which contains a wealth of information about the company. In this paper, we propose an explainable deep-learning model, called FinBERT-XRC, that takes a 10-K report as input, and automatically assesses the post-event return volatility risk of its associated company. In contrast to previous systems, our proposed model simultaneously offers explanations of its classification decision at three different levels: the word, sentence, and corpus levels. By doing so, our model provides a comprehensive interpretation of its prediction to end users. This is particularly important in financial domains, where the transparency and accountability of algorithmic predictions play a vital role in their application to decision-making processes.

Looking at how social values are represented in fairy tales can give insights about the variations in communication of values across cultures. We study how values are communicated in fairy tales from Portugal, Italy and Germany using a technique called word embedding with a compass to quantify vocabulary differences and commonalities. We study how these three national traditions differ in their explicit references to values. To do this, we specify a list of value-charged tokens, consider their word stems and analyse the distance between these in a bespoke pre-trained Word2Vec model. We triangulate and critically discuss the validity of the resulting hypotheses emerging from this quantitative model. Our claim is that this is a reusable and reproducible method for the study of the values explicitly referenced in historical corpora. Finally, our preliminary findings hint at a shared cultural understanding and the expression of values such as Benevolence, Conformity, and Universalism across the studied cultures, suggesting the potential existence of a pan-European cultural memory.