This book provides a broad overview of Natural Language Generation (NLG), including technology, user requirements, evaluation, and real-world applications. The focus is on concepts and insights which hopefully will remain relevant for many years, not on the latest LLM innovations. It draws on decades of work by the author and others on NLG. The book has the following chapters: Introduction to NLG; Rule-Based NLG; Machine Learning and Neural NLG; Requirements; Evaluation; Safety, Maintenance, and Testing; and Applications. All chapters include examples and anecdotes from the author's personal experiences, and end with a Further Reading section. The book should be especially useful to people working on applied NLG, including NLG researchers, people in other fields who want to use NLG, and commercial developers. It will not however be useful to people who want to understand the latest LLM technology. There is a companion site with more information at https://ehudreiter.com/book/

Maintaining security in IoT systems depends on intrusion detection since these networks' sensitivity to cyber-attacks is growing. Based on the IoT23 dataset, this study explores the use of several Machine Learning (ML) and Deep Learning (DL) along with the hybrid models for binary and multi-class intrusion detection. The standalone machine and deep learning models like Random Forest (RF), Extreme Gradient Boosting (XGBoost), Artificial Neural Network (ANN), K-Nearest Neighbors (KNN), Support Vector Machine (SVM), and Convolutional Neural Network (CNN) were used. Furthermore, two hybrid models were created by combining machine learning techniques: RF, XGBoost, AdaBoost, KNN, and SVM and these hybrid models were voting based hybrid classifier. Where one is for binary, and the other one is for multi-class classification. These models vi were tested using precision, recall, accuracy, and F1-score criteria and compared the performance of each model. This work thoroughly explains how hybrid, standalone ML and DL techniques could improve IDS (Intrusion Detection System) in terms of accuracy and scalability in IoT (Internet of Things).

School of Physical and Mathematical Sciences, Nanyang Technological University, Singapore 637371 Inferring causal models from observed correlations is a challenging task, crucial to many areas of science. In order to alleviate the effort, it is important to know whether symmetries in the observations correspond to symmetries in the underlying realization. Via an explicit example, we answer this question in the negative. We use a tripartite probability distribution over binary events that is realized by using three (different) independent sources of classical randomness. We prove that even removing the condition that the sources distribute systems described by classical physics, the requirements that i) the sources distribute the same physical systems, ii) these physical systems respect relativistic causality, and iii) the correlations are the observed ones, are incompatible.

Accurate and efficient modeling of Earth's ionosphere has a significant impact on research and operational communities due to its effects on radio communications, radar performance, [1, 2, 3] and satellite drag [4]. Success in forecasting key parameters such as the F2 layer critical frequency (foF2) and height (hmF2) and the total electron content (TEC) allows one to anticipate and mitigate the impacts of ionospheric variability on such systems. Over the past decades, many modeling approaches have been developed to predict these ionospheric parameters with increasing accuracy and skill. These models may be broadly categorized as empirical, physics-based, and, more recently, machine learning methods. Empirical models often rely on extensive historical datasets to establish statistical relationships between ionospheric parameters and geophysical variables. The International Reference Ionosphere (IRI) model [5] is a widely used standard that provides monthly averages of various ionospheric parameters based on many decades of past observations. IRI has seen continual development and improvements over the years, adding a host of submodels used to capture specific aspects of the ionosphere such as the CCIR [6, 7] and URSI [8] foF2 models for representing the diurnal variations of the peak plasma density across the globe, the AMTB [9] and SHU-2015 [10] models for even more harmonic expansions of hmF2, and NeQuick 2 [11] for improved topside electron density accuracy and thus better estimates of TEC [12, 13]. So, while large empirical models like IRI continue to improve, the number of these available options needed to address each domain and source of variance in the ionosphere also grows, and choosing the appropriate settings may be prohibitive without expert knowledge of each submodel.

Reasoning about images with rich text, such as charts and documents, is a critical application of vision-language models (VLMs). However, VLMs often struggle in these domains due to the scarcity of diverse text-rich vision-language data. To address this challenge, we present CoSyn, a framework that leverages the coding capabilities of text-only large language models (LLMs) to automatically create synthetic text-rich multimodal data. Given input text describing a target domain (e.g., "nutrition fact labels"), CoSyn prompts an LLM to generate code (Python, HTML, LaTeX, etc.) for rendering synthetic images. With the underlying code as textual representations of the synthetic images, CoSyn can generate high-quality instruction-tuning data, again relying on a text-only LLM. Using CoSyn, we constructed a dataset comprising 400K images and 2.7M rows of vision-language instruction-tuning data. Comprehensive experiments on seven benchmarks demonstrate that models trained on our synthetic data achieve state-of-the-art performance among competitive open-source models, including Llama 3.2, and surpass proprietary models such as GPT-4V and Gemini 1.5 Flash. Furthermore, CoSyn can produce synthetic pointing data, enabling VLMs to ground information within input images, showcasing its potential for developing multimodal agents capable of acting in real-world environments.

A common use of NLP is to facilitate the understanding of large document collections, with a shift from using traditional topic models to Large Language Models. Yet the effectiveness of using LLM for large corpus understanding in real-world applications remains under-explored. This study measures the knowledge users acquire with unsupervised, supervised LLM-based exploratory approaches or traditional topic models on two datasets. While LLM-based methods generate more human-readable topics and show higher average win probabilities than traditional models for data exploration, they produce overly generic topics for domain-specific datasets that do not easily allow users to learn much about the documents. Adding human supervision to the LLM generation process improves data exploration by mitigating hallucination and over-genericity but requires greater human effort. In contrast, traditional. models like Latent Dirichlet Allocation (LDA) remain effective for exploration but are less user-friendly. We show that LLMs struggle to describe the haystack of large corpora without human help, particularly domain-specific data, and face scaling and hallucination limitations due to context length constraints. Dataset available at https://huggingface. co/datasets/zli12321/Bills.

As artificial intelligence scales, the concepts of alignment, agency, and autonomy have become central to AI safety, governance, and control. However, even in human contexts, these terms lack universal definitions, varying across disciplines such as philosophy, psychology, law, computer science, mathematics, and political science. This inconsistency complicates their application to AI, where differing interpretations lead to conflicting approaches in system design and regulation. This paper traces the historical, philosophical, and technical evolution of these concepts, emphasizing how their definitions influence AI development, deployment, and oversight. We argue that the urgency surrounding AI alignment and autonomy stems not only from technical advancements but also from the increasing deployment of AI in high-stakes decision making. Using Agentic AI as a case study, we examine the emergent properties of machine agency and autonomy, highlighting the risks of misalignment in real-world systems. Through an analysis of automation failures (Tesla Autopilot, Boeing 737 MAX), multi-agent coordination (Metas CICERO), and evolving AI architectures (DeepMinds AlphaZero, OpenAIs AutoGPT), we assess the governance and safety challenges posed by frontier AI.

This paper explores the intersection of artificial intelligence and higher education administration, focusing on liberal arts colleges (LACs). It examines AI's opportunities and challenges in academic and student affairs, legal compliance, and accreditation processes, while also addressing the ethical considerations of AI deployment in mission-driven institutions. Considering AI's value pluralism and potential allocative or representational harms caused by algorithmic bias, LACs must ensure AI aligns with its mission and principles. The study highlights other strategies for responsible AI integration, balancing innovation with institutional values.

--In the realm of target tracking, performance evaluation plays a pivotal role in the design, comparison, and analytics of trackers. Compared with the traditional trajectory composed of a set of point-estimates obtained by a tracker in the measurement time-series, the trajectory that our series of studies including this paper pursued is given by a curve function of time (FoT). The trajectory FoT provides complete information of the movement of the target over time and can be used to infer the state corresponding to arbitrary time, not only at the measurement time. However, there are no metrics available for comparing and evaluating the trajectory FoT . T o address this lacuna, we propose a metric denominated as the spatiotemporal-aligned trajectory integral distance (Star-ID). The Star-ID associates and aligns the estimated and actual trajectories in the spatio-temporal domain and distinguishes between the time-aligned and unaligned segments in calculating the spatial divergence including false alarm, miss-detection and localization errors. The effectiveness of the proposed distance metric and the time-averaged version is validated through theoretical analysis and numerical examples of a single target or multiple targets. UL TI-target tracking (MTT) is an intricate process that entails the sequential estimation of both the cardinality (number of targets) and the kinematic states of multiple targets, where both parameters are potentially time-variant [1], [2], [3]. It has been a key technology in the applications of autonomous driving, guidance and defense systems, traffic control, and robotics.

AI agents are AI systems that can achieve complex goals autonomously. Assessing the level of agent autonomy is crucial for understanding both their potential benefits and risks. Current assessments of autonomy often focus on specific risks and rely on run-time evaluations - observations of agent actions during operation. We introduce a code-based assessment of autonomy that eliminates the need to run an AI agent to perform specific tasks, thereby reducing the costs and risks associated with run-time evaluations. Using this code-based framework, the orchestration code used to run an AI agent can be scored according to a taxonomy that assesses attributes of autonomy: impact and oversight. We demonstrate this approach with the AutoGen framework and select applications. Language model research and product attention focuses on creating Artificial Intelligence systems capable of flexibly planning and acting to influence environments over time ('AI agents') (Wang et al., 2024; Kapoor et al., 2024).