High sample complexity has long been a challenge for RL. On the other hand, humans learn to perform tasks not only from interaction or demonstrations, but also by reading unstructured text documents, e.g., instruction manuals. Instruction manuals and wiki pages are among the most abundant data that could inform agents of valuable features and policies or task-specific environmental dynamics and reward structures. Therefore, we hypothesize that the ability to utilize human-written instruction manuals to assist learning policies for specific tasks should lead to a more efficient and better-performing agent. We propose the Read and Reward framework. Read and Reward speeds up RL algorithms on Atari games by reading manuals released by the Atari game developers. Our framework consists of a QA Extraction module that extracts and summarizes relevant information from the manual and a Reasoning module that evaluates object-agent interactions based on information from the manual. An auxiliary reward is then provided to a standard A2C RL agent, when interaction is detected. Experimentally, various RL algorithms obtain significant improvement in performance and training speed when assisted by our design.

Graph neural networks are prominent models for representation learning over graph-structured data. While the capabilities and limitations of these models are well-understood for simple graphs, our understanding remains incomplete in the context of knowledge graphs. Our goal is to provide a systematic understanding of the landscape of graph neural networks for knowledge graphs pertaining to the prominent task of link prediction. Our analysis entails a unifying perspective on seemingly unrelated models and unlocks a series of other models. The expressive power of various models is characterized via a corresponding relational Weisfeiler-Leman algorithm. This analysis is extended to provide a precise logical characterization of the class of functions captured by a class of graph neural networks. The theoretical findings presented in this paper explain the benefits of some widely employed practical design choices, which are validated empirically.

In recent years, XAI researchers have been formalizing proposals and developing new methods to explain black box models, with no general consensus in the community on which method to use to explain these models, with this choice being almost directly linked to the popularity of a specific method. Methods such as Ciu, Dalex, Eli5, Lofo, Shap and Skater emerged with the proposal to explain black box models through global rankings of feature relevance, which based on different methodologies, generate global explanations that indicate how the model's inputs explain its predictions. In this context, 41 datasets, 4 tree-ensemble algorithms (Light Gradient Boosting, CatBoost, Random Forest, and Gradient Boosting), and 6 XAI methods were used to support the launch of a new XAI method, called eXirt, based on Item Response Theory - IRT and aimed at tree-ensemble black box models that use tabular data referring to binary classification problems. In the first set of analyses, the 164 global feature relevance ranks of the eXirt were compared with 984 ranks of the other XAI methods present in the literature, seeking to highlight their similarities and differences. In a second analysis, exclusive explanations of the eXirt based on Explanation-by-example were presented that help in understanding the model trust. Thus, it was verified that eXirt is able to generate global explanations of tree-ensemble models and also local explanations of instances of models through IRT, showing how this consolidated theory can be used in machine learning in order to obtain explainable and reliable models.

Responsible AI must be able to make decisions that consider human values and can be justified by human morals. Operationalising normative ethical principles inferred from philosophy supports responsible reasoning. We survey computer science literature and develop a taxonomy of 23 normative ethical principles which can be operationalised in AI. We describe how each principle has previously been operationalised, highlighting key themes that AI practitioners seeking to implement ethical principles should be aware of. We envision that this taxonomy will facilitate the development of methodologies to incorporate normative ethical principles in responsible AI systems.

Within network science, a widely applicable and important inference task is to understand how the behavior of interactions between different units (nodes) within the network depend on their latent characteristics. This occurs within a wide array of disciplines, from sociological (Freeman, 2004) to biological (Luo et al., 2007) networks. One simple and interpretable model for such a task is the stochastic block model (SBM) (Holland et al., 1983) which assumes that nodes within the network are assigned a discrete community label. Edges between nodes in the network are then formed independently across all pairs of edges, conditional on these community assignments. While such a model is simplistic, it and various extensions, such as the degree corrected SBM (DCSBM), used to handle degree heterogenity (Karrer and Newman, 2011), and mixed-membership SBMs, to allow for more complex community structures (Airoldi, Blei, Fienberg, and Xing, 2008), have seen a wide degree of empirical success (Latouche et al., 2011; Legramanti et al., 2022; Airoldi, Blei, Fienberg, Xing, and Jaakkola, 2006). One restriction of the stochastic block model and its generalizations is the requirement for a discrete community assignment as a latent representation of the units within the network. While the statistical community has previously considered more flexible latent representations (Hoff et al., 2002), over the past decade, there have been significant advancements in general embedding methods for networks, which produce general vector representations of units within a network, and generally achieve start-of-the-art performance in downstream tasks for node classification and link prediction. An early example of such a method is spectral clustering (Ng et al., 2001), which constructs an embedding of the nodes in the network from an eigendecomposition of the graph Laplacian. The k smallest non zero eigenvectors provides a k dimensional representation of each of the nodes in the network.

To achieve a highly agile and flexible production, it is envisioned that industrial production systems gradually become more decentralized, interconnected, and intelligent. Within this vision, production assets collaborate with each other, exhibiting a high degree of autonomy. Furthermore, knowledge about individual production assets is readily available throughout their entire life-cycles. To realize this vision, adequate use of information technology is required. Two commonly applied software paradigms in this context are Software Agents (referred to as Agents) and Digital Twins (DTs). This work presents a systematic comparison of Agents and DTs in industrial applications. The goal of the study is to determine the differences, similarities, and potential synergies between the two paradigms. The comparison is based on the purposes for which Agents and DTs are applied, the properties and capabilities exhibited by these software paradigms, and how they can be allocated within the Reference Architecture Model Industry 4.0. The comparison reveals that Agents are commonly employed in the collaborative planning and execution of production processes, while DTs typically play a more passive role in monitoring production resources and processing information. Although these observations imply characteristic sets of capabilities and properties for both Agents and DTs, a clear and definitive distinction between the two paradigms cannot be made. Instead, the analysis indicates that production assets utilizing a combination of Agents and DTs would demonstrate high degrees of intelligence, autonomy, sociability, and fidelity. To achieve this, further standardization is required, particularly in the field of DTs.

In this paper, we establish a benchmark named HalluQA (Chinese Hallucination Question-Answering) to measure the hallucination phenomenon in Chinese large language models. HalluQA contains 450 meticulously designed adversarial questions, spanning multiple domains, and takes into account Chinese historical culture, customs, and social phenomena. During the construction of HalluQA, we consider two types of hallucinations: imitative falsehoods and factual errors, and we construct adversarial samples based on GLM-130B and ChatGPT. For evaluation, we design an automated evaluation method using GPT-4 to judge whether a model output is hallucinated. We conduct extensive experiments on 24 large language models, including ERNIE-Bot, Baichuan2, ChatGLM, Qwen, SparkDesk and etc. Out of the 24 models, 18 achieved non-hallucination rates lower than 50%. This indicates that HalluQA is highly challenging. We analyze the primary types of hallucinations in different types of models and their causes. Additionally, we discuss which types of hallucinations should be prioritized for different types of models.

Despite their groundbreaking performance for many generative modeling tasks, diffusion models have fallen short on discrete data domains such as natural language. Crucially, standard diffusion models rely on the well-established theory of score matching, but efforts to generalize this to discrete structures have not yielded the same empirical gains. In this work, we bridge this gap by proposing score entropy, a novel discrete score matching loss that is more stable than existing methods, forms an ELBO for maximum likelihood training, and can be efficiently optimized with a denoising variant. We scale our Score Entropy Discrete Diffusion models (SEDD) to the experimental setting of GPT-2, achieving highly competitive likelihoods while also introducing distinct algorithmic advantages. In particular, when comparing similarly sized SEDD and GPT-2 models, SEDD attains comparable perplexities (normally within $+10\%$ of and sometimes outperforming the baseline). Furthermore, SEDD models learn a more faithful sequence distribution (around $4\times$ better compared to GPT-2 models with ancestral sampling as measured by large models), can trade off compute for generation quality (needing only $16\times$ fewer network evaluations to match GPT-2), and enables arbitrary infilling beyond the standard left to right prompting.

Adaptive importance sampling (AIS) algorithms are widely used to approximate expectations with respect to complicated target probability distributions. When the target has heavy tails, existing AIS algorithms can provide inconsistent estimators or exhibit slow convergence, as they often neglect the target's tail behaviour. To avoid this pitfall, we propose an AIS algorithm that approximates the target by Student-t proposal distributions. We adapt location and scale parameters by matching the escort moments - which are defined even for heavy-tailed distributions - of the target and the proposal. These updates minimize the $\alpha$-divergence between the target and the proposal, thereby connecting with variational inference. We then show that the $\alpha$-divergence can be approximated by a generalized notion of effective sample size and leverage this new perspective to adapt the tail parameter with Bayesian optimization. We demonstrate the efficacy of our approach through applications to synthetic targets and a Bayesian Student-t regression task on a real example with clinical trial data.

In the absence of readily available labeled data for a given sequence labeling task and language, annotation projection has been proposed as one of the possible strategies to automatically generate annotated data. Annotation projection has often been formulated as the task of transporting, on parallel corpora, the labels pertaining to a given span in the source language into its corresponding span in the target language. In this paper we present T-Projection, a novel approach for annotation projection that leverages large pretrained text-to-text language models and state-of-the-art machine translation technology. T-Projection decomposes the label projection task into two subtasks: (i) A candidate generation step, in which a set of projection candidates using a multilingual T5 model is generated and, (ii) a candidate selection step, in which the generated candidates are ranked based on translation probabilities. We conducted experiments on intrinsic and extrinsic tasks in 5 Indo-European and 8 low-resource African languages. We demostrate that T-projection outperforms previous annotation projection methods by a wide margin. We believe that T-Projection can help to automatically alleviate the lack of high-quality training data for sequence labeling tasks. Code and data are publicly available.