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/

Large language models (LLMs) are capable of generating coherent summaries from very long contexts given a user query. Extracting and properly citing evidence spans could help improve the transparency and reliability of these summaries. At the same time, LLMs suffer from positional biases in terms of which information they understand and attend to, which could affect evidence citation. Whereas previous work has focused on evidence citation with predefined levels of granularity (e.g. sentence, paragraph, document, etc.), we propose the task of long-context query focused summarization with unstructured evidence citation. We show how existing systems struggle to generate and properly cite unstructured evidence from their context, and that evidence tends to be "lost-in-the-middle". To help mitigate this, we create the Summaries with Unstructured Evidence Text dataset (SUnsET), a synthetic dataset generated using a novel domain-agnostic pipeline which can be used as supervision to adapt LLMs to this task. We demonstrate across 5 LLMs of different sizes and 4 datasets with varying document types and lengths that LLMs adapted with SUnsET data generate more relevant and factually consistent evidence than their base models, extract evidence from more diverse locations in their context, and can generate more relevant and consistent summaries.

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.

While Large Language Models (LLMs) can exhibit impressive proficiency in isolated, short-term tasks, they often fail to maintain coherent performance over longer time horizons. In this paper, we present Vending-Bench, a simulated environment designed to specifically test an LLM-based agent's ability to manage a straightforward, long-running business scenario: operating a vending machine. Agents must balance inventories, place orders, set prices, and handle daily fees - tasks that are each simple but collectively, over long horizons (>20M tokens per run) stress an LLM's capacity for sustained, coherent decision-making. Our experiments reveal high variance in performance across multiple LLMs: Claude 3.5 Sonnet and o3-mini manage the machine well in most runs and turn a profit, but all models have runs that derail, either through misinterpreting delivery schedules, forgetting orders, or descending into tangential "meltdown" loops from which they rarely recover. We find no clear correlation between failures and the point at which the model's context window becomes full, suggesting that these breakdowns do not stem from memory limits. Apart from highlighting the high variance in performance over long time horizons, Vending-Bench also tests models' ability to acquire capital, a necessity in many hypothetical dangerous AI scenarios. We hope the benchmark can help in preparing for the advent of stronger AI systems.

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.

The expansion of artificial intelligence (AI) has raised concerns about transparency, accountability, and interpretability, with counterfactual reasoning emerging as a key approach to addressing these issues. However, current mathematical, technological, and causal methodologies rely on externalization techniques that normalize feature relationships within a single coordinate space, often distorting intrinsic interactions. This study proposes the Convergent Fusion Paradigm (CFP) theory, a framework integrating mathematical, technological, and causal perspectives to provide a more precise and comprehensive analysis of feature relationships. CFP theory introduces Hilbert space and backward causation to reinterpret the feature relationships as emergent structures, offering a potential solution to the common cause problem -- a fundamental challenge in causal modeling. From a mathematical -- technical perspective, it utilizes a Riemannian manifold-based framework, thereby improving the structural representation of high- and low-dimensional data interactions. From a causal inference perspective, CFP theory adopts abduction as a methodological foundation, employing Hilbert space for a dynamic causal reasoning approach, where causal relationships are inferred abductively, and feature relationships evolve as emergent properties. Ultimately, CFP theory introduces a novel AI modeling methodology that integrates Hilbert space, backward causation, and Riemannian geometry, strengthening AI governance and transparency in counterfactual reasoning.

We study the use of large language models (LLMs) to both evaluate and greenwash corporate climate disclosures. First, we investigate the use of the LLM-as-a-Judge (LLMJ) methodology for scoring company-submitted reports on emissions reduction targets and progress. Second, we probe the behavior of an LLM when it is prompted to greenwash a response subject to accuracy and length constraints. Finally, we test the robustness of the LLMJ methodology against responses that may be greenwashed using an LLM. We find that two LLMJ scoring systems, numerical rating and pairwise comparison, are effective in distinguishing high-performing companies from others, with the pairwise comparison system showing greater robustness against LLM-greenwashed responses.

As the use of large language model (LLM) agents continues to grow, their safety vulnerabilities have become increasingly evident. Extensive benchmarks evaluate various aspects of LLM safety by defining the safety relying heavily on general standards, overlooking user-specific standards. However, safety standards for LLM may vary based on a user-specific profiles rather than being universally consistent across all users. This raises a critical research question: Do LLM agents act safely when considering user-specific safety standards? Despite its importance for safe LLM use, no benchmark datasets currently exist to evaluate the user-specific safety of LLMs. To address this gap, we introduce U-SAFEBENCH, the first benchmark designed to assess user-specific aspect of LLM safety. Our evaluation of 18 widely used LLMs reveals current LLMs fail to act safely when considering user-specific safety standards, marking a new discovery in this field. To address this vulnerability, we propose a simple remedy based on chain-of-thought, demonstrating its effectiveness in improving user-specific safety. Our benchmark and code are available at https://github.com/yeonjun-in/U-SafeBench.

User specifications or legal frameworks often require information to be removed from pretrained models, including large language models (LLMs). This requires deleting or "forgetting" a set of data points from an already-trained model, which typically degrades its performance on other data points. Thus, a balance must be struck between removing information and keeping the model's other abilities intact, with a failure to balance this trade-off leading to poor deletion or an unusable model. To this end, we propose UPCORE (Utility-Preserving Coreset Selection), a method-agnostic data selection framework for mitigating collateral damage during unlearning. Finding that the model damage is correlated with the variance of the model's representations on the forget set, we selectively prune the forget set to remove outliers, thereby minimizing model degradation after unlearning. We evaluate UPCORE across three standard unlearning methods consistently achieving a superior balance between the competing objectives of deletion efficacy and model preservation. To better evaluate this trade-off, we introduce a new metric, measuring the area-under-the-curve (AUC) across standard metrics. We find that UPCORE improves both standard metrics and AUC, benefitting from positive transfer between the coreset and pruned points while reducing negative transfer from the forget set to points outside of it.

Recent copyright agreements between AI companies and content creators have highlighted the need for precise control over language models' ability to reproduce copyrighted content. While existing approaches rely on either complete concept removal through unlearning or simple output filtering, we propose Obliviate, a novel post-training technique that selectively prevents verbatim reproduction of specific text while preserving semantic understanding. Obliviate operates by selecting tokens within memorized sequences and modifying the model's probability distribution to prevent exact reproduction while maintaining contextual understanding. We evaluate Obliviate on multiple large language models (LLaMA-3.1 8B, LLaMA-3.1-instruct 8B, Qwen-2.5-7B, and Yi-1.5 6B) across both synthetic memorization tasks and organic copyright content. Our results demonstrate that Obliviate achieves orders of magnitude reduction, e.g., 100x, in verbatim memorization while maintaining model performance within 1% of baseline on standard benchmarks (HellaSwag, MMLU, TruthfulQA, and Winogrande). This makes Obliviate particularly suitable for practical deployment scenarios where companies need to efficiently address copyright concerns in pretrained models without compromising their general capabilities.