Ship design is a years-long process that requires balancing complex design trade-offs to create a ship that is efficient and effective. Finding new ways to improve the ship design process can lead to significant cost savings for ship building and operation. One promising technology is generative artificial intelligence, which has been shown to reduce design cycle time and create novel, high-performing designs. In literature review, generative artificial intelligence has been shown to generate ship hulls; however, ship design is particularly difficult as the hull of a ship requires the consideration of many objectives. This paper presents a study on the generation of parametric ship hull designs using a parametric diffusion model that considers multiple objectives and constraints for the hulls. This denoising diffusion probabilistic model (DDPM) generates the tabular parametric design vectors of a ship hull for evaluation. In addition to a tabular DDPM, this paper details adding guidance to improve the quality of generated ship hull designs. By leveraging classifier guidance, the DDPM produced feasible parametric ship hulls that maintain the coverage of the initial training dataset of ship hulls with a 99.5% rate, a 149x improvement over random sampling of the design vector parameters across the design space. Parametric ship hulls produced with performance guidance saw an average of 91.4% reduction in wave drag coefficients and an average of a 47.9x relative increase in the total displaced volume of the hulls compared to the mean performance of the hulls in the training dataset. The use of a DDPM to generate parametric ship hulls can reduce design time by generating high-performing hull designs for future analysis. These generated hulls have low drag and high volume, which can reduce the cost of operating a ship and increase its potential to generate revenue.

Engaging in the deliberate generation of abnormal outputs from large language models (LLMs) by attacking them is a novel human activity. This paper presents a thorough exposition of how and why people perform such attacks. Using a formal qualitative methodology, we interviewed dozens of practitioners from a broad range of backgrounds, all contributors to this novel work of attempting to cause LLMs to fail. We relate and connect this activity between its practitioners' motivations and goals; the strategies and techniques they deploy; and the crucial role the community plays. As a result, this paper presents a grounded theory of how and why people attack large language models: LLM red teaming in the wild.

A Federated Learning (FL) system typically consists of two core processing entities: the federation controller and the learners. The controller is responsible for managing the execution of FL workflows across learners and the learners for training and evaluating federated models over their private datasets. While executing an FL workflow, the FL system has no control over the computational resources or data of the participating learners. Still, it is responsible for other operations, such as model aggregation, task dispatching, and scheduling. These computationally heavy operations generally need to be handled by the federation controller. Even though many FL systems have been recently proposed to facilitate the development of FL workflows, most of these systems overlook the scalability of the controller. To meet this need, we designed and developed a novel FL system called MetisFL, where the federation controller is the first-class citizen. MetisFL re-engineers all the operations conducted by the federation controller to accelerate the training of large-scale FL workflows. By quantitatively comparing MetisFL against other state-of-the-art FL systems, we empirically demonstrate that MetisFL leads to a 10-fold wall-clock time execution boost across a wide range of challenging FL workflows with increasing model sizes and federation sites.

A common approach to evaluating the significance of a collection of $p$-values combines them with a pooling function, in particular when the original data are not available. These pooled $p$-values convert a sample of $p$-values into a single number which behaves like a univariate $p$-value. To clarify discussion of these functions, a telescoping series of alternative hypotheses are introduced that communicate the strength and prevalence of non-null evidence in the $p$-values before general pooling formulae are discussed. A pattern noticed in the UMP pooled $p$-value for a particular alternative motivates the definition and discussion of central and marginal rejection levels at $\alpha$. It is proven that central rejection is always greater than or equal to marginal rejection, motivating a quotient to measure the balance between the two for pooled $p$-values. A combining function based on the $\chi^2_{\kappa}$ quantile transformation is proposed to control this quotient and shown to be robust to mis-specified parameters relative to the UMP. Different powers for different parameter settings motivate a map of plausible alternatives based on where this pooled $p$-value is minimized.

With the rise of social media, users are exposed to many misleading claims. However, the pervasive noise inherent in these posts presents a challenge in identifying precise and prominent claims that require verification. Extracting the important claims from such posts is arduous and time-consuming, yet it is an underexplored problem. Here, we aim to bridge this gap. We introduce a novel task, Claim Normalization (aka ClaimNorm), which aims to decompose complex and noisy social media posts into more straightforward and understandable forms, termed normalized claims. We propose CACN, a pioneering approach that leverages chain-of-thought and claim check-worthiness estimation, mimicking human reasoning processes, to comprehend intricate claims. Moreover, we capitalize on the in-context learning capabilities of large language models to provide guidance and to improve claim normalization. To evaluate the effectiveness of our proposed model, we meticulously compile a comprehensive real-world dataset, CLAN, comprising more than 6k instances of social media posts alongside their respective normalized claims. Our experiments demonstrate that CACN outperforms several baselines across various evaluation measures. Finally, our rigorous error analysis validates CACN's capabilities and pitfalls.

Red-teaming has been a widely adopted way to evaluate the harmful behavior of Large Language Models (LLMs). It aims to jailbreak a model's safety behavior to make it act as a helpful agent disregarding the harmfulness of the query. Existing methods are primarily based on input text-based red-teaming such as adversarial prompts, low-resource prompts, or contextualized prompts to condition the model in a way to bypass its safety guardrails. An effective jailbreak has the potential to uncover hidden harmful information and biases in the model that are left untreated or newly introduced by its safety training. However, prompt-based attacks fail to provide such a diagnosis owing to their low attack success rate and applicability to specific models. It simply (instruction) tunes the model parameters to break its guardrails that are not deeply rooted in the model's behavior. GPT to the point where it responds with an 88% success rate to harmful queries from two safety benchmark datasets. Large Language Models (LLMs) have shown emerging zero-shot capabilities with an increase in size (Wei et al., 2022; Brown et al., 2020) i.e., beyond a point where quantitative changes lead to qualitative changes in the model. As exciting as it is to observe the significance (utility) of such models to people, an adversary can find these systems highly useful to achieve a malicious goal. Moreover, such systems tend to inherit biases from humans through the datasets used for their construction. Thus, before deploying these systems for wide public use, it is important to make them unharmful and unbiased while maintaining their generic utility.

Urban flood risk emerges from complex and nonlinear interactions among multiple features related to flood hazard, flood exposure, and social and physical vulnerabilities, along with the complex spatial flood dependence relationships. Existing approaches for characterizing urban flood risk, however, are primarily based on flood plain maps, focusing on a limited number of features, primarily hazard and exposure features, without consideration of feature interactions or the dependence relationships among spatial areas. To address this gap, this study presents an integrated urban flood-risk rating model based on a novel unsupervised graph deep learning model (called FloodRisk-Net). FloodRisk-Net is capable of capturing spatial dependence among areas and complex and nonlinear interactions among flood hazards and urban features for specifying emergent flood risk. Using data from multiple metropolitan statistical areas (MSAs) in the United States, the model characterizes their flood risk into six distinct city-specific levels. The model is interpretable and enables feature analysis of areas within each flood-risk level, allowing for the identification of the three archetypes shaping the highest flood risk within each MSA. Flood risk is found to be spatially distributed in a hierarchical structure within each MSA, where the core city disproportionately bears the highest flood risk. Multiple cities are found to have high overall flood-risk levels and low spatial inequality, indicating limited options for balancing urban development and flood-risk reduction. Relevant flood-risk reduction strategies are discussed considering ways that the highest flood risk and uneven spatial distribution of flood risk are formed.

Reliably controlling the behavior of large language models is a pressing open problem. Existing methods include supervised finetuning, reinforcement learning from human feedback, prompt engineering and guided decoding. We instead investigate activation engineering: modifying activations at inference-time to predictably alter model behavior. We bias the forward pass with a 'steering vector' implicitly specified through natural language. Past work learned these steering vectors; our Activation Addition (ActAdd) method instead computes them by taking the activation differences which result from pairs of prompts. We demonstrate ActAdd on GPT-2 on OpenWebText and ConceptNet, and replicate the effect on Llama-13B and GPT-J-6B. Our approach yields inference-time control over high-level properties of output & preserves performance on off-target topics. The method requires far less compute and implementation effort than finetuning and RLHF, allows for natural language specification by users, and its overhead scales naturally with model size.

The ability of deep learning (DL) approaches to learn generalised signal and noise models, coupled with their fast inference on GPUs, holds great promise for enhancing gravitational-wave (GW) searches in terms of speed, parameter space coverage, and search sensitivity. However, the opaque nature of DL models severely harms their reliability. In this work, we meticulously develop a DL model stage-wise and work towards improving its robustness and reliability. First, we address the problems in maintaining the purity of training data by deriving a new metric that better reflects the visual strength of the 'chirp' signal features in the data. Using a reduced, smooth representation obtained through a variational auto-encoder (VAE), we build a classifier to search for compact binary coalescence (CBC) signals. Our tests on real LIGO data show an impressive performance of the model. However, upon probing the robustness of the model through adversarial attacks, its simple failure modes were identified, underlining how such models can still be highly fragile. As a first step towards bringing robustness, we retrain the model in a novel framework involving a generative adversarial network (GAN). Over the course of training, the model learns to eliminate the primary modes of failure identified by the adversaries. Although absolute robustness is practically impossible to achieve, we demonstrate some fundamental improvements earned through such training, like sparseness and reduced degeneracy in the extracted features at different layers inside the model. We show that these gains are achieved at practically zero loss in terms of model performance on real LIGO data before and after GAN training. Through a direct search on 8.8 days of LIGO data, we recover two significant CBC events from GWTC-2.1, GW190519_153544 and GW190521_074359. We also report the search sensitivity obtained from an injection study.

Unsupervised clustering is widely used to explore large corpora, but existing formulations neither consider the users' goals nor explain clusters' meanings. We propose a new task formulation, "Goal-Driven Clustering with Explanations" (GoalEx), which represents both the goal and the explanations as free-form language descriptions. For example, to categorize the errors made by a summarization system, the input to GoalEx is a corpus of annotator-written comments for system-generated summaries and a goal description "cluster the comments based on why the annotators think the summary is imperfect.''; the outputs are text clusters each with an explanation ("this cluster mentions that the summary misses important context information."), which relates to the goal and precisely explain which comments should (not) belong to a cluster. To tackle GoalEx, we prompt a language model with "[corpus subset] + [goal] + Brainstorm a list of explanations each representing a cluster."; then we classify whether each sample belongs to a cluster based on its explanation; finally, we use integer linear programming to select a subset of candidate clusters to cover most samples while minimizing overlaps. Under both automatic and human evaluation on corpora with or without labels, our method produces more accurate and goal-related explanations than prior methods. We release our data and implementation at https://github.com/ZihanWangKi/GoalEx.