Objective: This article offers a taxonomy of generative artificial intelligence (AI) for health economics and outcomes research (HEOR), explores its emerging applications, and outlines methods to enhance the accuracy and reliability of AI-generated outputs. Methods: The review defines foundational generative AI concepts and highlights current HEOR applications, including systematic literature reviews, health economic modeling, real-world evidence generation, and dossier development. Approaches such as prompt engineering (zero-shot, few-shot, chain-of-thought, persona pattern prompting), retrieval-augmented generation, model fine-tuning, and the use of domain-specific models are introduced to improve AI accuracy and reliability. Results: Generative AI shows significant potential in HEOR, enhancing efficiency, productivity, and offering novel solutions to complex challenges. Foundation models are promising in automating complex tasks, though challenges remain in scientific reliability, bias, interpretability, and workflow integration. The article discusses strategies to improve the accuracy of these AI tools. Conclusion: Generative AI could transform HEOR by increasing efficiency and accuracy across various applications. However, its full potential can only be realized by building HEOR expertise and addressing the limitations of current AI technologies. As AI evolves, ongoing research and innovation will shape its future role in the field.

Users often interact with large language models through black-box inference APIs, both for closed- and open-weight models (e.g., Llama models are popularly accessed via Amazon Bedrock and Azure AI Studio). In order to cut costs or add functionality, API providers may quantize, watermark, or finetune the underlying model, changing the output distribution -- often without notifying users. We formalize detecting such distortions as Model Equality Testing, a two-sample testing problem, where the user collects samples from the API and a reference distribution and conducts a statistical test to see if the two distributions are the same. We find that tests based on the Maximum Mean Discrepancy between distributions are powerful for this task: a test built on a simple string kernel achieves a median of 77.4% power against a range of distortions, using an average of just 10 samples per prompt. We then apply this test to commercial inference APIs for four Llama models, finding that 11 out of 31 endpoints serve different distributions than reference weights released by Meta.

To unlock access to stronger winds, the offshore wind industry is advancing with significantly larger and taller wind turbines. This massive upscaling motivates a departure from univariate wind forecasting methods that traditionally focused on a single representative height. To fill this gap, we propose DeepMIDE--a statistical deep learning method which jointly models the offshore wind speeds across space, time, and height. DeepMIDE is formulated as a multi-output integro-difference equation model with a multivariate, nonstationary, and state-dependent kernel characterized by a set of advection vectors that encode the physics of wind field formation and propagation. Embedded within DeepMIDE, an advanced deep learning architecture learns these advection vectors from high dimensional streams of exogenous weather information, which, along with other parameters, are plugged back into the statistical model for probabilistic multi-height space-time forecasting. Tested on real-world data from future offshore wind energy sites in the Northeastern United States, the wind speed and power forecasts from DeepMIDE are shown to outperform those from prevalent time series, spatio-temporal, and deep learning methods.

The development of large language models and multi-modal models has enabled the appealing idea of generating novel molecules from text descriptions. Generative modeling would shift the paradigm from relying on large-scale chemical screening to find molecules with desired properties to directly generating those molecules. However, multi-modal models combining text and molecules are often trained from scratch, without leveraging existing high-quality pretrained models. That approach consumes more computational resources and prohibits model scaling. In contrast, we propose a lightweight adapter-based strategy named Chemical Language Model Linker (ChemLML). ChemLML blends the two single domain models and obtains conditional molecular generation from text descriptions while still operating in the specialized embedding spaces of the molecular domain. ChemLML can tailor diverse pretrained text models for molecule generation by training relatively few adapter parameters. We find that the choice of molecular representation used within ChemLML, SMILES versus SELFIES, has a strong influence on conditional molecular generation performance. SMILES is often preferable despite not guaranteeing valid molecules. We raise issues in using the large PubChem dataset of molecules and their associated descriptions for evaluating molecule generation and provide a filtered version of the dataset as a generation test set. To demonstrate how ChemLML could be used in practice, we generate candidate protein inhibitors and use docking to assess their quality.

Adversarial machine learning concerns situations in which learners face attacks from active adversaries. Such scenarios arise in applications such as spam email filtering, malware detection and fake-image generation, where security methods must be actively updated to keep up with the ever improving generation of malicious data. We model these interactions between the learner and the adversary as a game and formulate the problem as a pessimistic bilevel optimisation problem with the learner taking the role of the leader. The adversary, modelled as a stochastic data generator, takes the role of the follower, generating data in response to the classifier. While existing models rely on the assumption that the adversary will choose the least costly solution leading to a convex lower-level problem with a unique solution, we present a novel model and solution method which do not make such assumptions. We compare these to the existing approach and see significant improvements in performance suggesting that relaxing these assumptions leads to a more realistic model.

In recent years, the widespread adoption of Large Language Models (LLMs) has sparked interest in their potential for application within the military domain. However, the current generation of LLMs demonstrate sub-optimal performance on Army use cases, due to the prevalence of domain-specific vocabulary and jargon. In order to fully leverage LLMs in-domain, many organizations have turned to fine-tuning to circumvent the prohibitive costs involved in training new LLMs from scratch. In light of this trend, we explore the viability of adapting open-source LLMs for usage in the Army domain in order to address their existing lack of domain-specificity. Our investigations have resulted in the creation of three distinct generations of TRACLM, a family of LLMs fine-tuned by The Research and Analysis Center (TRAC), Army Futures Command (AFC). Through continuous refinement of our training pipeline, each successive iteration of TRACLM displayed improved capabilities when applied to Army tasks and use cases. Furthermore, throughout our fine-tuning experiments, we recognized the need for an evaluation framework that objectively quantifies the Army domain-specific knowledge of LLMs. To address this, we developed MilBench, an extensible software framework that efficiently evaluates the Army knowledge of a given LLM using tasks derived from doctrine and assessments. We share preliminary results, models, methods, and recommendations on the creation of TRACLM and MilBench. Our work significantly informs the development of LLM technology across the DoD and augments senior leader decisions with respect to artificial intelligence integration.

Clear legal language forms the backbone of a contract for numerous reasons. Disputes often arise between contract parties where ambiguous language has been used and parties often disagree on the meaning or effect of the words. Unambiguous language can also be important where there is an imbalance of bargaining strength between the parties, for instance where a business is contracting with a consumer, where the law actually requires plain language to be used. Thus, plain language minimises misinterpretation and prevents future litigation. Contracts become ambiguous when the language used is vague, imprecise, or open to multiple interpretations and this is due to the vast number of synonyms in the English Language which creates differences in interpretation between the meaning of the language. Ambiguity has always formed a prevalent issue in case-law, with a large percentage of cases based on ambiguous language. Thus, from an outside perspective the legal sector should look forward to ways of reducing this.

During pre-training, the Text-to-Image (T2I) diffusion models encode factual knowledge into their parameters. These parameterized facts enable realistic image generation, but they may become obsolete over time, thereby misrepresenting the current state of the world. Knowledge editing techniques aim to update model knowledge in a targeted way. However, facing the dual challenges posed by inadequate editing datasets and unreliable evaluation criterion, the development of T2I knowledge editing encounter difficulties in effectively generalizing injected knowledge. In this work, we design a T2I knowledge editing framework by comprehensively spanning on three phases: First, we curate a dataset \textbf{CAKE}, comprising paraphrase and multi-object test, to enable more fine-grained assessment on knowledge generalization. Second, we propose a novel criterion, \textbf{adaptive CLIP threshold}, to effectively filter out false successful images under the current criterion and achieve reliable editing evaluation. Finally, we introduce \textbf{MPE}, a simple but effective approach for T2I knowledge editing. Instead of tuning parameters, MPE precisely recognizes and edits the outdated part of the conditioning text-prompt to accommodate the up-to-date knowledge. A straightforward implementation of MPE (Based on in-context learning) exhibits better overall performance than previous model editors. We hope these efforts can further promote faithful evaluation of T2I knowledge editing methods.

Traumatic brain injury (TBI) presents a significant public health challenge, often resulting in mortality or lasting disability. Predicting outcomes such as mortality and Functional Status Scale (FSS) scores can enhance treatment strategies and inform clinical decision-making. This study applies supervised machine learning (ML) methods to predict mortality and FSS scores using a real-world dataset of 300 pediatric TBI patients from the University of Colorado School of Medicine. The dataset captures clinical features, including demographics, injury mechanisms, and hospitalization outcomes. Eighteen ML models were evaluated for mortality prediction, and thirteen models were assessed for FSS score prediction. Performance was measured using accuracy, ROC AUC, F1-score, and mean squared error. Logistic regression and Extra Trees models achieved high precision in mortality prediction, while linear regression demonstrated the best FSS score prediction. Feature selection reduced 103 clinical variables to the most relevant, enhancing model efficiency and interpretability. This research highlights the role of ML models in identifying high-risk patients and supporting personalized interventions, demonstrating the potential of data-driven analytics to improve TBI care and integrate into clinical workflows.

Israel launched its first-ever strikes against Houthi rebels in Yemen just days after Jerusalem vowed revenge for a drone strike on Tel Aviv. Russia has been aiding the Houthis' assault on Western shipping lanes in the Red Sea by providing them targeting data. As the Houthis ramped up their strikes on the U.S. and other nations' postures in the region after the Oct. 7 attack on Israel, Russians offered satellite data allowing them to expand their strikes, take out multimillion-dollar U.S. drones and hit ships sailing through the Red Sea and the Suez Canal, through which 12% of global trade passes, according to a Wall Street Journal report. Each munition used to intercept a Houthi strike costs the U.S. upwards of between 1 million and 4 million. The data passed through Iran's Revolutionary Guard Corps (IRGC).