Misinformation is all over the internet, including the -- at times -- chaos that is X (formerly Twitter). AI bots have a habit of adding to it. Now, with barely two months left until the presidential election, an update to Grok, X's premium chatbot, could curve some of it (after being called out for said election misinformation). Grok will now direct anyone with an election-related query to Vote.org, a non-partisan website operated through a partnership between the US government, the US Election Assistance Commission and the Cybersecurity and Infrastructure Security Agency. The catalyst for change came on July 21, only hours after President Biden announced his decision not to seek reelection, when Grok falsely posted that the ballot deadline had passed in nine states, implying officials couldn't change the democratic candidate. Minnesota Secretary of State Steve Simon had staff attempt to contact X about the error, to which they received the response, "Busy now, please check back later."

A Ukrainian drone attack has set an oil depot in Russia's southern region of Rostov alight, the authorities said. On Wednesday, regional Governor Vasily Golubev confirmed the overnight strike, saying on the Telegram messaging app that firefighters were extinguishing the blaze at the depot in Rostov's Kamensky district, with no casualties reported. Russia's Ministry of Defence earlier said air defence units destroyed four drones over the region overnight, without mentioning the attack on the oil depot. Three tanks were burning at the oil depot after two drones fell in the area, according to the Baza Telegram channel, which is close to Russian security services. Ukraine's strike marked its latest attack on Russian oil and gas facilities in retaliation for attacks on its energy infrastructure.

Klarna - which is based in Sweden, and has two UK offices - disclosed its job-cutting plans as it announced interim results which showed it increased its revenue by 27% to 13.3 billion Swedish krona ( 990 million). "Our proven scale efficiencies have been enhanced by our investment in AI, which has driven down operating expenses and improved gross profits," it said. It comes as unions have warned of mass job losses amid the growth of AI and are calling for legislation to protect workers. Mr Siemiatkowski said Klarna would reduce its headcount through what he called "natural attrition" - effectively a hiring freeze, where staff aren't replaced after they leave. Typically this means the people that remain are left with an increased workload. But Mr Siemiatkowski contended that AI would be replacing this work, and even claimed it was a potential "positive development" for some individuals who may be paid more.

Advanced by state Sen. Scott Wiener, a Democrat, the proposal would mandate safety testing for many of the most advanced AI models that cost more than 100 million to develop or those that require a defined amount of computing power. Developers of AI software operating in the state would also need to outline methods for turning off the AI models if they go awry, effectively a kill switch.

Trustworthy Artificial Intelligence (TAI) integrates ethics that align with human values, looking at their influence on AI behaviour and decision-making. Primarily dependent on self-assessment, TAI evaluation aims to ensure ethical standards and safety in AI development and usage. This paper reviews the current TAI evaluation methods in the literature and offers a classification, contributing to understanding self-assessment methods in this field.

Artificial intelligence (AI) creates opportunities for assessments, such as efficiencies for item generation and scoring of spoken and written responses. At the same time, it poses risks (such as bias in AI-generated item content). Responsible AI (RAI) practices aim to mitigate risks associated with AI. This chapter addresses the critical role of RAI practices in achieving test quality (appropriateness of test score inferences), and test equity (fairness to all test takers). To illustrate, the chapter presents a case study using the Duolingo English Test (DET), an AI-powered, high-stakes English language assessment. The chapter discusses the DET RAI standards, their development and their relationship to domain-agnostic RAI principles. Further, it provides examples of specific RAI practices, showing how these practices meaningfully address the ethical principles of validity and reliability, fairness, privacy and security, and transparency and accountability standards to ensure test equity and quality.

To accurately compute data-based prediction of Hamiltonian systems, especially the long-term evolution of such systems, it is essential to utilize methods that preserve the structure of the equations over time. We consider a case that is particularly challenging for data-based methods: systems with interacting parts that do not reduce to pure momentum evolution. Such systems are essential in scientific computations. For example, any discretization of a continuum elastic rod can be viewed as interacting elements that can move and rotate in space, with each discrete element moving on the group of rotations and translations $SE(3)$. We develop a novel method of data-based computation and complete phase space learning of such systems. We follow the original framework of \emph{SympNets} (Jin et al, 2020) building the neural network from canonical phase space mappings, and transformations that preserve the Lie-Poisson structure (\emph{LPNets}) as in (Eldred et al, 2024). We derive a novel system of mappings that are built into neural networks for coupled systems. We call such networks Coupled Lie-Poisson Neural Networks, or \emph{CLPNets}. We consider increasingly complex examples for the applications of CLPNets: rotation of two rigid bodies about a common axis, the free rotation of two rigid bodies, and finally the evolution of two connected and interacting $SE(3)$ components. Our method preserves all Casimir invariants of each system to machine precision, irrespective of the quality of the training data, and preserves energy to high accuracy. Our method also shows good resistance to the curse of dimensionality, requiring only a few thousand data points for all cases studied, with the effective dimension varying from three to eighteen. Additionally, the method is highly economical in memory requirements, requiring only about 200 parameters for the most complex case considered.

This thesis provides methods and analysis of models which make progress on this goal. The techniques outlined are task agnostic, and should provide benefit when used with nearly any transformer LM. We introduce two new finetuning methods which add new capabilities to the models they are used on. The first adds a recurrence mechanism, which removes the fixed-window sized constraint and improves the efficiency of a transformer decoder. The second allows masked language models (MLMs) to be used for initialization of both the encoder and decoder of a non-autoregressive sequence-to-sequence transformer, opening up generative applications of models which were previously only used for natural language understanding tasks. We also introduce two new techniques for improving the quality of predictions of any transformer decoder without additional finetuning. One, hidden state optimization, can be applied to any transformer decoder to improve the quality of predictions at inference time, especially for few-shot classification. The other, conditional beam search, allows practitioners to search for natural language generation (NLG) model outputs with high likelihood while conditioning on the event that the output is not degenerate (e.g. empty, repetitive, etc.). Finally, we provide theoretical and empirical insights on the divergence of model-likelihood and output quality which has widely been observed in prior work. These insights apply to any model which represents a distribution over text, and apply to language models which are not transformers or even autoregressive. We argue that the NLP community has, to some extent, misunderstood the implications of these findings, and encourage a point of view which has more nuance.

The remarkable success of large language models (LLMs) across various multi-modality applications is well established. However, integrating large language models with humans, or brain dynamics, remains relatively unexplored. In this paper, we introduce BELT-2, a pioneering multi-task model designed to enhance both encoding and decoding performance from EEG signals. To bolster the quality of the EEG encoder, BELT-2 is the first work to innovatively 1) adopt byte-pair encoding (BPE)-level EEG-language alignment and 2) integrate multi-task training and decoding in the EEG domain. Inspired by the idea of \textbf{\textit{Bridging the Brain with GPT}}, we further connect the multi-task EEG encoder with LLMs by utilizing prefix-tuning on intermediary output from the EEG encoder. These innovative efforts make BELT-2 a pioneering breakthrough, making it the first work in the field capable of decoding coherent and readable sentences from non-invasive brain signals. Our experiments highlight significant advancements over prior techniques in both quantitative and qualitative measures, achieving a decoding performance with a BLEU-1 score of 52.2\% on the ZuCo dataset. Furthermore, BELT-2 shows a remarkable improvement ranging from 31\% to 162\% on other translation benchmarks. Codes can be accessed via the provided anonymous link~\footnote{https://anonymous.4open.science/r/BELT-2-0048}.

In this paper, we investigate the use of probabilistic graphical models, specifically stochastic blockmodels, for the purpose of hierarchical entity clustering on knowledge graphs. These models, seldom used in the Semantic Web community, decompose a graph into a set of probability distributions. The parameters of these distributions are then inferred allowing for their subsequent sampling to generate a random graph. In a non-parametric setting, this allows for the induction of hierarchical clusterings without prior constraints on the hierarchy's structure. Specifically, this is achieved by the integration of the Nested Chinese Restaurant Process and the Stick Breaking Process into the generative model. In this regard, we propose a model leveraging such integration and derive a collapsed Gibbs sampling scheme for its inference. To aid in understanding, we describe the steps in this derivation and provide an implementation for the sampler. We evaluate our model on synthetic and real-world datasets and quantitatively compare against benchmark models. We further evaluate our results qualitatively and find that our model is capable of inducing coherent cluster hierarchies in small scale settings. The work presented in this paper provides the first step for the further application of stochastic blockmodels for knowledge graphs on a larger scale. We conclude the paper with potential avenues for future work on more scalable inference schemes.