Modeling Socioeconomic Systems: ABMs Socioeconomic systems exhibit intricate patterns of interaction and adaptation, e.g., between social groups and to changing environmental and economic conditions, reflecting a degree of complexity that challenges current methods for analysis and prediction of these systems [1, 2]. Modeling the complexity of these systems often requires detailed knowledge of the interacting components, their associated scales, and sufficient resolution of these details such that bottom-up emergent properties can be observed. Agent-based models (ABMs) are a computational modeling tool to resolve these facets of complex social science problems. ABMs simulate a large number of agents in a shared environment: through agent-to-agent and agent-environment interactions, ABMs relate system-wide emergent properties to individual behaviors [3]. This work was supported by the Multisector Dynamics program area of the U.S. Department of Energy, Office of Science, Office of Biological and Environmental Research as part of the multi-program, collaborative Integrated Coastal Modeling (ICoM) project at PNNL, a multi-program national laboratory operated by Battelle for the U.S. Department of Energy under contract DE-AC05-76RL01830.

This article presents a new machine unlearning approach that utilizes multiple Generative Adversarial Network (GAN) based models. The proposed method comprises two phases: i) data reorganization in which synthetic data using the GAN model is introduced with inverted class labels of the forget datasets, and ii) fine-tuning the pre-trained model. The GAN models consist of two pairs of generators and discriminators. The generator discriminator pairs generate synthetic data for the retain and forget datasets. Then, a pre-trained model is utilized to get the class labels of the synthetic datasets. The class labels of synthetic and original forget datasets are inverted. Finally, all combined datasets are used to fine-tune the pre-trained model to get the unlearned model. We have performed the experiments on the CIFAR-10 dataset and tested the unlearned models using Membership Inference Attacks (MIA). The inverted class labels procedure and synthetically generated data help to acquire valuable information that enables the model to outperform state-of-the-art models and other standard unlearning classifiers.

The recent emergence of Large Language Models (LLMs) has heralded a new era of human-AI interaction. These sophisticated models, exemplified by Chat-GPT and its successors, have exhibited remarkable capabilities in language understanding. However, as these LLMs have undergone exponential growth, a crucial dimension that remains understudied is the personalization of these models. Large foundation models such as GPT-3 etc. focus on creating a universal model that serves a broad range of tasks and users. This approach emphasizes the model's generalization capabilities, treating users as a collective rather than as distinct individuals. While practical for many common applications, this one-size-fits-all approach often fails to address the rich tapestry of human diversity and individual needs. To explore this issue we introduce the PEFT-U Benchmark: a new dataset for building and evaluating NLP models for user personalization. \datasetname{} consists of a series of user-centered tasks containing diverse and individualized expressions where the preferences of users can potentially differ for the same input. Using PEFT-U, we explore the challenge of efficiently personalizing LLMs to accommodate user-specific preferences in the context of diverse user-centered tasks.

Most state-of-the-art AI applications in atmospheric science are based on classic deep learning approaches. However, such approaches cannot automatically integrate multiple complicated procedures to construct an intelligent agent, since each functionality is enabled by a separate model learned from independent climate datasets. The emergence of foundation models, especially multimodal foundation models, with their ability to process heterogeneous input data and execute complex tasks, offers a substantial opportunity to overcome this challenge. In this report, we want to explore a central question - how the state-of-the-art foundation model, i.e., GPT-4o, performs various atmospheric scientific tasks. Toward this end, we conduct a case study by categorizing the tasks into four main classes, including climate data processing, physical diagnosis, forecast and prediction, and adaptation and mitigation. For each task, we comprehensively evaluate the GPT-4o's performance along with a concrete discussion. We hope that this report may shed new light on future AI applications and research in atmospheric science.

It is challenging to scale time series forecasting models such that they forecast accurately for multiple distinct domains and datasets, all with potentially different underlying collection procedures (e.g., sample resolution), patterns (e.g., periodicity), and prediction requirements (e.g., reconstruction vs. forecasting). We call this general task universal forecasting. Existing methods usually assume that input data is regularly sampled, and they forecast to pre-determined horizons, resulting in failure to generalise outside of the scope of their training. We propose the DAM - a neural model that takes randomly sampled histories and outputs an adjustable basis composition as a continuous function of time for forecasting to non-fixed horizons. It involves three key components: (1) a flexible approach for using randomly sampled histories from a long-tail distribution, that enables an efficient global perspective of the underlying temporal dynamics while retaining focus on the recent history; (2) a transformer backbone that is trained on these actively sampled histories to produce, as representational output, (3) the basis coefficients of a continuous function of time. We show that a single univariate DAM, trained on 25 time series datasets, either outperformed or closely matched existing SoTA models at multivariate long-term forecasting across 18 datasets, including 8 held-out for zero-shot transfer, even though these models were trained to specialise for each dataset-horizon combination. This single DAM excels at zero-shot transfer and very-long-term forecasting, performs well at imputation, is interpretable via basis function composition and attention, can be tuned for different inference-cost requirements, is robust to missing and irregularly sampled data {by design}.

GermanPartiesQA: Benchmarking Commercial Large Language Models for Political Bias and Sycophancy Jan Batzner 1, 3 *, V olker Stocker 1, 2, Stefan Schmid 2, 1, Gjergji Kasneci 3 1 Weizenbaum Institute Berlin 2 Technical University Berlin 3 Technical University Munich Abstract LLMs are changing the way humans create and interact with content, potentially affecting citizens' political opinions and voting decisions. As LLMs increasingly shape our digital information ecosystems, auditing to evaluate biases, sycophancy, or steerability has emerged as an active field of research. In this paper, we evaluate and compare the alignment of six LLMs by OpenAI, Anthropic, and Cohere with German party positions and evaluate sycophancy based on a prompt experiment. We contribute to evaluating political bias and sycophancy in multi-party systems across major commercial LLMs. First, we develop the benchmark dataset GermanPar-tiesQA based on the V oting Advice Application W ahl-o-Mat covering 10 state and 1 national elections between 2021 and 2023. In our study, we find a left-green tendency across all examined LLMs. We then conduct our prompt experiment for which we use the benchmark and sociodemographic data of leading German parliamentarians to evaluate changes in LLMs responses. To differentiate between sycophancy and steerabilty, we use "I am [politician X], ... " and "Y ou are [politician X], ... " prompts. Against our expectations, we do not observe notable differences between prompting "I am" and "Y ou are". While our findings underscore that LLM responses can be ideologically steered with political personas, they suggest that observed changes in LLM outputs could be better described as personalization to the given context rather than sycophancy. 1 INTRODUCTION Large language models (LLMs) are changing the way humans create and consume content. The unprecedented pace with which end-users have adopted ChatGPT [14] has not only brought LLMs and generative AI to public attention but has emphasized their increasing potential to influence societal, economic, and political outcomes. Generative AI applications can impact citizens in various ways directly or indirectly as they may be consumer-facing (e.g., LLM-based chat interfaces like ChatGPT) or not (e.g., users may interact with content created by or with the support of LLMs, with the role of LLMs being less transparent to citizens).

Learning models whose predictions are invariant under multiple environments is a promising approach for out-of-distribution generalization. Such models are trained to extract features $X_{\text{inv}}$ where the conditional distribution $Y \mid X_{\text{inv}}$ of the label given the extracted features does not change across environments. Invariant models are also supposed to generalize to shifts in the marginal distribution $p(X_{\text{inv}})$ of the extracted features $X_{\text{inv}}$, a type of shift we call an $\textit{invariant covariate shift}$. However, we show that proposed methods for learning invariant models underperform under invariant covariate shift, either failing to learn invariant models$\unicode{x2014}$even for data generated from simple and well-studied linear-Gaussian models$\unicode{x2014}$or having poor finite-sample performance. To alleviate these problems, we propose $\textit{weighted risk invariance}$ (WRI). Our framework is based on imposing invariance of the loss across environments subject to appropriate reweightings of the training examples. We show that WRI provably learns invariant models, i.e. discards spurious correlations, in linear-Gaussian settings. We propose a practical algorithm to implement WRI by learning the density $p(X_{\text{inv}})$ and the model parameters simultaneously, and we demonstrate empirically that WRI outperforms previous invariant learning methods under invariant covariate shift.

Previous research on testing the vulnerabilities in Large Language Models (LLMs) using adversarial attacks has primarily focused on nonsensical prompt injections, which are easily detected upon manual or automated review (e.g., via byte entropy). However, the exploration of innocuous human-understandable malicious prompts augmented with adversarial injections remains limited. In this research, we explore converting a nonsensical suffix attack into a sensible prompt via a situation-driven contextual re-writing. This allows us to show suffix conversion without any gradients, using only LLMs to perform the attacks, and thus better understand the scope of possible risks. We combine an independent, meaningful adversarial insertion and situations derived from movies to check if this can trick an LLM. The situations are extracted from the IMDB dataset, and prompts are defined following a few-shot chain-of-thought prompting. Our approach demonstrates that a successful situation-driven attack can be executed on both open-source and proprietary LLMs. We find that across many LLMs, as few as 1 attempt produces an attack and that these attacks transfer between LLMs.

The deep operator network (DeepONet) is a popular neural operator architecture that has shown promise in solving partial differential equations (PDEs) by using deep neural networks to map between infinite-dimensional function spaces. In the absence of labeled datasets, we utilize the PDE residual loss to learn the physical system, an approach known as physics-informed DeepONet. This method faces significant computational challenges, primarily due to the curse of dimensionality, as the computational cost increases exponentially with finer discretization. In this paper, we introduce the Separable DeepONet framework to address these challenges and improve scalability for high-dimensional PDEs. Our approach involves a factorization technique where sub-networks handle individual one-dimensional coordinates, thereby reducing the number of forward passes and the size of the Jacobian matrix. By using forward-mode automatic differentiation, we further optimize the computational cost related to the Jacobian matrix. As a result, our modifications lead to a linear scaling of computational cost with discretization density, making Separable DeepONet suitable for high-dimensional PDEs. We validate the effectiveness of the separable architecture through three benchmark PDE models: the viscous Burgers equation, Biot's consolidation theory, and a parametrized heat equation. In all cases, our proposed framework achieves comparable or improved accuracy while significantly reducing computational time compared to conventional DeepONet. These results demonstrate the potential of Separable DeepONet in efficiently solving complex, high-dimensional PDEs, advancing the field of physics-informed machine learning.

Graph self-training (GST), which selects and assigns pseudo-labels to unlabeled nodes, is popular for tackling label sparsity in graphs. However, recent study on homophily graphs show that GST methods could introduce and amplify distribution shift between training and test nodes as they tend to assign pseudo-labels to nodes they are good at. As GNNs typically perform better on homophilic nodes, there could be potential shifts towards homophilic pseudo-nodes, which is underexplored. Our preliminary experiments on heterophilic graphs verify that these methods can cause shifts in homophily ratio distributions, leading to \textit{training bias} that improves performance on homophilic nodes while degrading it on heterophilic ones. Therefore, we study a novel problem of reducing homophily ratio distribution shifts during self-training on heterophilic graphs. A key challenge is the accurate calculation of homophily ratios and their distributions without extensive labeled data. To tackle them, we propose a novel Heterophily-aware Distribution Consistency-based Graph Self-Training (HC-GST) framework, which estimates homophily ratios using soft labels and optimizes a selection vector to align pseudo-nodes with the global homophily ratio distribution. Extensive experiments on both homophilic and heterophilic graphs show that HC-GST effectively reduces training bias and enhances self-training performance.