Retrosynthesis consists of breaking down a chemical compound recursively step-by-step into molecular precursors until a set of commercially available molecules is found with the goal to provide a synthesis route. Its two primary research directions, single-step retrosynthesis prediction, which models the chemical reaction logic, and multi-step synthesis planning, which tries to find the correct sequence of reactions, are inherently intertwined. Still, this connection is not reflected in contemporary research. In this work, we combine these two major research directions by applying multiple single-step retrosynthesis models within multi-step synthesis planning and analyzing their impact using public and proprietary reaction data. We find a disconnection between high single-step performance and potential route-finding success, suggesting that single-step models must be evaluated within synthesis planning in the future. Furthermore, we show that the commonly used single-step retrosynthesis benchmark dataset USPTO-50k is insufficient as this evaluation task does not represent model performance and scalability on larger and more diverse datasets. For multi-step synthesis planning, we show that the choice of the single-step model can improve the overall success rate of synthesis planning by up to +28% compared to the commonly used baseline model. Finally, we show that each single-step model finds unique synthesis routes, and differs in aspects such as route-finding success, the number of found synthesis routes, and chemical validity, making the combination of single-step retrosynthesis prediction and multi-step synthesis planning a crucial aspect when developing future methods.

Transformer-based language models (TLMs) have widely been recognized to be a cutting-edge technology for the successful development of deep-learning-based solutions to problems and applications that require natural language processing and understanding. Like for other textual domains, TLMs have indeed pushed the state-of-the-art of AI approaches for many tasks of interest in the legal domain. Despite the first Transformer model being proposed about six years ago, there has been a rapid progress of this technology at an unprecedented rate, whereby BERT and related models represent a major reference, also in the legal domain. This article provides the first systematic overview of TLM-based methods for AI-driven problems and tasks in the legal sphere. A major goal is to highlight research advances in this field so as to understand, on the one hand, how the Transformers have contributed to the success of AI in supporting legal processes, and on the other hand, what are the current limitations and opportunities for further research development.

Ensuring alignment, which refers to making models behave in accordance with human intentions [1,2], has become a critical task before deploying large language models (LLMs) in real-world applications. For instance, OpenAI devoted six months to iteratively aligning GPT-4 before its release [3]. However, a major challenge faced by practitioners is the lack of clear guidance on evaluating whether LLM outputs align with social norms, values, and regulations. This obstacle hinders systematic iteration and deployment of LLMs. To address this issue, this paper presents a comprehensive survey of key dimensions that are crucial to consider when assessing LLM trustworthiness. The survey covers seven major categories of LLM trustworthiness: reliability, safety, fairness, resistance to misuse, explainability and reasoning, adherence to social norms, and robustness. Each major category is further divided into several sub-categories, resulting in a total of 29 sub-categories. Additionally, a subset of 8 sub-categories is selected for further investigation, where corresponding measurement studies are designed and conducted on several widely-used LLMs. The measurement results indicate that, in general, more aligned models tend to perform better in terms of overall trustworthiness. However, the effectiveness of alignment varies across the different trustworthiness categories considered. This highlights the importance of conducting more fine-grained analyses, testing, and making continuous improvements on LLM alignment. By shedding light on these key dimensions of LLM trustworthiness, this paper aims to provide valuable insights and guidance to practitioners in the field. Understanding and addressing these concerns will be crucial in achieving reliable and ethically sound deployment of LLMs in various applications.

Online violence against children has increased globally recently, demanding urgent attention. Competent authorities manually analyze abuse complaints to comprehend crime dynamics and identify patterns. However, the manual analysis of these complaints presents a challenge because it exposes analysts to harmful content during the review process. Given these challenges, we present a novel solution, an automated tool designed to analyze children's sexual abuse reports comprehensively. By automating the analysis process, our tool significantly reduces the risk of exposure to harmful content by categorizing the reports on three dimensions: Subject, Degree of Criminality, and Damage. Furthermore, leveraging our multidisciplinary team's expertise, we introduce a novel approach to annotate the collected data, enabling a more in-depth analysis of the reports. This approach improves the comprehension of fundamental patterns and trends, enabling law enforcement agencies and policymakers to create focused strategies in the fight against children's violence.

Customising AI technologies to each user's preferences is fundamental to them functioning well. Unfortunately, current methods require too much user involvement and fail to capture their true preferences. In fact, to avoid the nuisance of manually setting preferences, users usually accept the default settings even if these do not conform to their true preferences. Norms can be useful to regulate behaviour and ensure it adheres to user preferences but, while the literature has thoroughly studied norms, most proposals take a formal perspective. Indeed, while there has been some research on constructing norms to capture a user's privacy preferences, these methods rely on domain knowledge which, in the case of AI technologies, is difficult to obtain and maintain. We argue that a new perspective is required when constructing norms, which is to exploit the large amount of preference information readily available from whole systems of users. Inspired by recommender systems, we believe that collaborative filtering can offer a suitable approach to identifying a user's norm preferences without excessive user involvement.

Google and Universal Music are negotiating a deal on how to license the voices and melodies of artists for artificial intelligence-generated songs. The artists would have a choice to opt in to the process. According to the Financial Times, the talks are at an early stage and there are no plans for an immediate product launch. The talks come after a popular and recent trend of fans using AI programs to make deepfake music that imitates artists' voices and cadence so it appears they are singing other people's songs or even new material. On TikTok, there are several viral videos of convincingly mimicked AI-made tracks of artists, usually without the consent of the artists' voices the creators are making.

The AI4GCC competition presents a bold step forward in the direction of integrating machine learning with traditional economic policy analysis. Below, we highlight two potential areas for improvement that could enhance the competition's ability to identify and evaluate proposed negotiation protocols. Firstly, we suggest the inclusion of an additional index that accounts for consumption/utility as part of the evaluation criteria. Secondly, we recommend further investigation into the learning dynamics of agents in the simulator and the game theoretic properties of outcomes from proposed negotiation protocols. We hope that these suggestions can be of use for future iterations of the competition/simulation.

Convolutional Neural Networks (CNNs) are models that are utilized extensively for the hierarchical extraction of features. Vision transformers (ViTs), through the use of a self-attention mechanism, have recently achieved superior modeling of global contextual information compared to CNNs. However, to realize their image classification strength, ViTs require substantial training datasets. Where the available training data are limited, current advanced multi-layer perceptrons (MLPs) can provide viable alternatives to both deep CNNs and ViTs. In this paper, we developed the SGU-MLP, a learning algorithm that effectively uses both MLPs and spatial gating units (SGUs) for precise land use land cover (LULC) mapping. Results illustrated the superiority of the developed SGU-MLP classification algorithm over several CNN and CNN-ViT-based models, including HybridSN, ResNet, iFormer, EfficientFormer and CoAtNet. The proposed SGU-MLP algorithm was tested through three experiments in Houston, USA, Berlin, Germany and Augsburg, Germany. The SGU-MLP classification model was found to consistently outperform the benchmark CNN and CNN-ViT-based algorithms. For example, for the Houston experiment, SGU-MLP significantly outperformed HybridSN, CoAtNet, Efficientformer, iFormer and ResNet by approximately 15%, 19%, 20%, 21%, and 25%, respectively, in terms of average accuracy. The code will be made publicly available at https://github.com/aj1365/SGUMLP

In 1950, the British computer scientist Alan Turing disputed whether human reasoning can be matched by computers: "Can machines think?" (TURING, 1950). Subsequently, he proposed the Turing Test to measure computer or artificial intelligence. In a Turing test, a human interrogator is presented with responses from a human and a computer (with the ability to generate written texts in real-time). If the interrogator cannot distinguish between the answers, the computer system passes the Turing Test. Although several computer programs and chatbots like Eliza demonstrated success in the Turing test ((Weizenbaum, 1966) (Güzeldere & Franchi, 1995)), these programs arguably used certain tricks to pass the test (Pinar Saygin et al., 2000) rather than demonstrating any significant intelligence. With the advancement in machine learning and natural language processing (NLP), chatbots have gained significant research attention and have been used for a variety of commercial and non-commercial applications ((Luo et al., 2022), (Adamopoulou & Moussiades, 2020), (Ranoliya et al., 2017), (Rahman et al., 2017), (Zhou et al., 2020)). Despite their vast adoption, most chatbots do not have personalization, and user satisfaction remains questionable (Følstad & Brandtzaeg, 2020). This limitation prompted researchers and developers to focus on chatbot engagement in making chatbots more conversational.

In recent years, federated learning (FL) has become a very popular paradigm for training distributed, large-scale, and privacy-preserving machine learning (ML) systems. In contrast to standard ML, where data must be collected at the exact location where training is performed, FL takes advantage of the computational capabilities of millions of edge devices to collaboratively train a shared, global model without disclosing their local private data. Specifically, in a typical FL system, the central server acts only as an orchestrator; it iteratively gathers and aggregates all the local models trained by each client on its private data until convergence. Although FL undoubtedly has several benefits over traditional ML (e.g., it protects private data ownership by design), it suffers from several weaknesses. One of the most critical challenges is to overcome the centralized orchestration of the classical FL client-server architecture, which is known to be vulnerable to single-point-of-failure risks and man-in-the-middle attacks, among others. To mitigate such exposure, decentralized FL solutions have emerged where all FL clients cooperate and communicate without a central server. This survey comprehensively summarizes and reviews existing decentralized FL approaches proposed in the literature. Furthermore, it identifies emerging challenges and suggests promising research directions in this under-explored domain.