Cyber-physical systems (CPSs) constitute the backbone of critical infrastructures such as power grids or water distribution networks. Operating failures in these systems can cause serious risks for society. To avoid or minimize downtime, operators require real-time awareness about critical incidents. However, online event identification in CPSs is challenged by the complex interdependency of numerous physical and digital components, requiring to take cyber attacks and physical failures equally into account. The online event identification problem is further complicated through the lack of historical observations of critical but rare events, and the continuous evolution of cyber attack strategies. This work introduces and demonstrates CyPhERS, a Cyber-Physical Event Reasoning System. CyPhERS provides real-time information pertaining the occurrence, location, physical impact, and root cause of potentially critical events in CPSs, without the need for historical event observations. Key novelty of CyPhERS is the capability to generate informative and interpretable event signatures of known and unknown types of both cyber attacks and physical failures. The concept is evaluated and benchmarked on a demonstration case that comprises a multitude of attack and fault events targeting various components of a CPS. The results demonstrate that the event signatures provide relevant and inferable information on both known and unknown event types.

This article presents a 5-level AI Capability Assessment Model (AI-CAM) and a related AI Capabilities Matrix (AI-CM) to assist practitioners in AI comprehension and adoption. These practical tools were developed with business executives, technologists, and other organisational stakeholders in mind. They are founded on a comprehensive conception of AI compared to those in other AI adoption models and are also open-source artefacts. Thus, the AI-CAM and AI-CM present an accessible resource to help inform organisational decision-makers on the capability requirements for (1) AI-based data analytics use cases based on machine learning technologies; (2) Knowledge representation to engineer and represent data, information and knowledge using semantic technologies; and (3) AI-based solutions that seek to emulate human reasoning and decision-making. The AI-CAM covers the core capability dimensions (business, data, technology, organisation, AI skills, risks, and ethical considerations) required at the five capability maturity levels to achieve optimal use of AI in organisations. The AI-CM details the related individual and team-level capabilities needed to reach each level in organisational AI capability; it, therefore, extends and enriches existing perspectives by introducing knowledge and skills requirements at all levels of an organisation. It posits three levels of AI proficiency: (1) Basic, for operational users who interact with AI and participate in AI adoption; (2) Advanced, for professionals who are charged with comprehending AI and developing related business models and strategies; and (3) Expert, for computer engineers, data scientists, and knowledge engineers participating in the design and implementation of AIbased technologies to support business use cases. In conclusion, the AI-CAM and AI-CM present a valuable resource for practitioners, businesses, and technologists, looking to innovate using AI technologies and maximise the return to their organisations.

Longitudinal Dialogues (LD) are the most challenging type of conversation for human-machine dialogue systems. LDs include the recollections of events, personal thoughts, and emotions specific to each individual in a sparse sequence of dialogue sessions. Dialogue systems designed for LDs should uniquely interact with the users over multiple sessions and long periods of time (e.g. weeks), and engage them in personal dialogues to elaborate on their feelings, thoughts, and real-life events. In this paper, we study the task of response generation in LDs. We evaluate whether general-purpose Pre-trained Language Models (PLM) are appropriate for this purpose. We fine-tune two PLMs, GePpeTto (GPT-2) and iT5, using a dataset of LDs. We experiment with different representations of the personal knowledge extracted from LDs for grounded response generation, including the graph representation of the mentioned events and participants. We evaluate the performance of the models via automatic metrics and the contribution of the knowledge via the Integrated Gradients technique. We categorize the natural language generation errors via human evaluations of contextualization, appropriateness and engagement of the user.

Thomas Haigh (thomas.haigh@gmail.com) is a professor of history at the University of Wisconsin--Milwaukee, WI, USA, and a Comenius visiting professor at Siegen University, Germany.

Today's powerful, robust SAT solvers have become primary tools for solving hard computational problems.

Scaling up language models has been empirically shown to improve performance on a wide range of downstream tasks. However, if we were to observe worse performance as a function of scale ("inverse scaling") on certain tasks, this would indicate that scaling can also encourage behaviors that are misaligned with human preferences. The Inverse Scaling Prize (McKenzie et al. 2022) identified eleven such inverse scaling tasks, evaluated on models of up to 280B parameters and up to 500 zettaFLOPs of training compute. This paper takes a closer look at these inverse scaling tasks. We evaluate models of up to 540B parameters, trained on five times more compute than those evaluated in the Inverse Scaling Prize. With this increased range of model sizes and training compute, only four out of the eleven tasks remain inverse scaling. Six out of the eleven tasks exhibit "U-shaped scaling", where performance decreases up to a certain size, and then increases again up to the largest model evaluated (the one remaining task displays positive scaling). In addition, we find that 1-shot examples and chain-of-thought can help mitigate undesirable scaling patterns even further. U-shaped scaling suggests that the inverse scaling trend observed in McKenzie et al. (2022) may not continue to hold for larger models, which we attribute to the presence of distractor tasks that only sufficiently large models can avoid.

Explainable question answering (XQA) aims to answer a given question and provide an explanation why the answer is selected. Existing XQA methods focus on reasoning on a single knowledge source, e.g., structured knowledge bases, unstructured corpora, etc. However, integrating information from heterogeneous knowledge sources is essential to answer complex questions. In this paper, we propose to leverage question decomposing for heterogeneous knowledge integration, by breaking down a complex question into simpler ones, and selecting the appropriate knowledge source for each sub-question. To facilitate reasoning, we propose a novel two-stage XQA framework, Reasoning over Hierarchical Question Decomposition Tree (RoHT). First, we build the Hierarchical Question Decomposition Tree (HQDT) to understand the semantics of a complex question; then, we conduct probabilistic reasoning over HQDT from root to leaves recursively, to aggregate heterogeneous knowledge at different tree levels and search for a best solution considering the decomposing and answering probabilities. The experiments on complex QA datasets KQA Pro and Musique show that our framework outperforms SOTA methods significantly, demonstrating the effectiveness of leveraging question decomposing for knowledge integration and our RoHT framework.

Few-shot learning is a challenging task that requires language models to generalize from limited examples. Large language models like GPT-3 and PaLM have made impressive progress in this area, but they still face difficulties in reasoning tasks such as GSM8K, a benchmark for arithmetic problems. To improve their reasoning skills, previous work has proposed to guide the language model with prompts that elicit a series of reasoning steps before giving the final answer, achieving a significant improvement on GSM8K from 17.9% to 58.1% in problem-solving rate. In this paper, we present DIVERSE (Diverse Verifier on Reasoning Step), a novel approach that further enhances the reasoning capability of language models. DIVERSE has three main components: first, it generates diverse prompts to explore different reasoning paths for the same question; second, it uses a verifier to filter out incorrect answers based on a weighted voting scheme; and third, it verifies each reasoning step individually instead of the whole chain. We evaluate DIVERSE on the latest language model code-davinci-002 and show that it achieves new state-of-the-art results on six of eight reasoning benchmarks (e.g., GSM8K 74.4% to 83.2%).

Although counterfactual reasoning is a fundamental aspect of intelligence, the lack of large-scale counterfactual open-domain question-answering (QA) benchmarks makes it difficult to evaluate and improve models on this ability. To address this void, we introduce the first such dataset, named IfQA, where each question is based on a counterfactual presupposition via an "if" clause. For example, if Los Angeles was on the east coast of the U.S., what would be the time difference between Los Angeles and Paris? Such questions require models to go beyond retrieving direct factual knowledge from the Web: they must identify the right information to retrieve and reason about an imagined situation that may even go against the facts built into their parameters. The IfQA dataset contains over 3,800 questions that were annotated annotated by crowdworkers on relevant Wikipedia passages. Empirical analysis reveals that the IfQA dataset is highly challenging for existing open-domain QA methods, including supervised retrieve-then-read pipeline methods (EM score 36.2), as well as recent few-shot approaches such as chain-of-thought prompting with GPT-3 (EM score 27.4). The unique challenges posed by the IfQA benchmark will push open-domain QA research on both retrieval and counterfactual reasoning fronts.

Game-based decision-making involves reasoning over both world dynamics and strategic interactions among the agents. Typically, empirical models capturing these respective aspects are learned and used separately. We investigate the potential gain from co-learning these elements: a world model for dynamics and an empirical game for strategic interactions. Empirical games drive world models toward a broader consideration of possible game dynamics induced by a diversity of strategy profiles. Conversely, world models guide empirical games to efficiently discover new strategies through planning. We demonstrate these benefits first independently, then in combination as realized by a new algorithm, Dyna-PSRO, that co-learns an empirical game and a world model. When compared to PSRO -- a baseline empirical-game building algorithm, Dyna-PSRO is found to compute lower regret solutions on partially observable general-sum games. In our experiments, Dyna-PSRO also requires substantially fewer experiences than PSRO, a key algorithmic advantage for settings where collecting player-game interaction data is a cost-limiting factor.