White matter alterations are increasingly implicated in neurological diseases and their progression. International-scale studies use diffusion-weighted magnetic resonance imaging (DW-MRI) to qualitatively identify changes in white matter microstructure and connectivity. Yet, quantitative analysis of DW-MRI data is hindered by inconsistencies stemming from varying acquisition protocols. There is a pressing need to harmonize the preprocessing of DW-MRI datasets to ensure the derivation of robust quantitative diffusion metrics across acquisitions. In the MICCAI-CDMRI 2023 QuantConn challenge, participants were provided raw data from the same individuals collected on the same scanner but with two different acquisitions and tasked with preprocessing the DW-MRI to minimize acquisition differences while retaining biological variation. Submissions are evaluated on the reproducibility and comparability of cross-acquisition bundle-wise microstructure measures, bundle shape features, and connectomics. The key innovations of the QuantConn challenge are that (1) we assess bundles and tractography in the context of harmonization for the first time, (2) we assess connectomics in the context of harmonization for the first time, and (3) we have 10x additional subjects over prior harmonization challenge, MUSHAC and 100x over SuperMUDI. We find that bundle surface area, fractional anisotropy, connectome assortativity, betweenness centrality, edge count, modularity, nodal strength, and participation coefficient measures are most biased by acquisition and that machine learning voxel-wise correction, RISH mapping, and NeSH methods effectively reduce these biases. In addition, microstructure measures AD, MD, RD, bundle length, connectome density, efficiency, and path length are least biased by these acquisition differences.

This report provides an initial look at partial results from the TREC 2024 Retrieval-Augmented Generation (RAG) Track. We have identified RAG evaluation as a barrier to continued progress in information access (and more broadly, natural language processing and artificial intelligence), and it is our hope that we can contribute to tackling the many challenges in this space. The central hypothesis we explore in this work is that the nugget evaluation methodology, originally developed for the TREC Question Answering Track in 2003, provides a solid foundation for evaluating RAG systems. As such, our efforts have focused on "refactoring" this methodology, specifically applying large language models to both automatically create nuggets and to automatically assign nuggets to system answers. We call this the AutoNuggetizer framework. Within the TREC setup, we are able to calibrate our fully automatic process against a manual process whereby nuggets are created by human assessors semi-manually and then assigned manually to system answers. Based on initial results across 21 topics from 45 runs, we observe a strong correlation between scores derived from a fully automatic nugget evaluation and a (mostly) manual nugget evaluation by human assessors. This suggests that our fully automatic evaluation process can be used to guide future iterations of RAG systems.

While current large language models have achieved a remarkable success, their data efficiency remains a challenge to overcome. Recently it has been suggested that child-directed speech (CDS) can improve training data efficiency of modern language models based on Transformer neural networks. However, it is not yet understood which specific properties of CDS are effective for training these models. In the context of the BabyLM Challenge, we focus on Variation Sets (VSs), sets of consecutive utterances expressing a similar intent with slightly different words and structures, which are ubiquitous in CDS. To assess the impact of VSs on training data efficiency, we augment CDS data with different proportions of artificial VSs and use these datasets to train an auto-regressive model, GPT-2. We find that the best proportion of VSs depends on the evaluation benchmark: BLiMP and GLUE scores benefit from the presence of VSs, but EWOK scores do not. Additionally, the results vary depending on multiple factors such as the number of epochs and the order of utterance presentation. Taken together, these findings suggest that VSs can have a beneficial influence on language models, while leaving room for further investigation.

With the continuous development of large language models (LLMs), transformer-based models have made groundbreaking advances in numerous natural language processing (NLP) tasks, leading to the emergence of a series of agents that use LLMs as their control hub. While LLMs have achieved success in various tasks, they face numerous security and privacy threats, which become even more severe in the agent scenarios. To enhance the reliability of LLM-based applications, a range of research has emerged to assess and mitigate these risks from different perspectives. To help researchers gain a comprehensive understanding of various risks, this survey collects and analyzes the different threats faced by these agents. To address the challenges posed by previous taxonomies in handling cross-module and cross-stage threats, we propose a novel taxonomy framework based on the sources and impacts. Additionally, we identify six key features of LLM-based agents, based on which we summarize the current research progress and analyze their limitations. Subsequently, we select four representative agents as case studies to analyze the risks they may face in practical use. Finally, based on the aforementioned analyses, we propose future research directions from the perspectives of data, methodology, and policy, respectively.

Understanding the text in legal documents can be challenging due to their complex structure and the inclusion of domain-specific jargon. Laws and regulations are often crafted in such a manner that engagement with them requires formal training, potentially leading to vastly different interpretations of the same texts. Linguistic complexity is an important contributor to the difficulties experienced by readers. Simplifying texts could enhance comprehension across a broader audience, not just among trained professionals. Various metrics have been developed to measure document readability. Therefore, we adopted a systematic review approach to examine the linguistic and readability metrics currently employed for legal and regulatory texts. A total of 3566 initial papers were screened, with 34 relevant studies found and further assessed. Our primary objective was to identify which current metrics were applied for evaluating readability within the legal field. Sixteen different metrics were identified, with the Flesch-Kincaid Grade Level being the most frequently used method. The majority of studies (73.5%) were found in the domain of "informed consent forms". From the analysis, it is clear that not all legal domains are well represented in terms of readability metrics and that there is a further need to develop more consensus on which metrics should be applied for legal documents.

Large language models (LLMs) excel in high-resource languages but face notable challenges in low-resource languages like Mongolian. This paper addresses these challenges by categorizing capabilities into language abilities (syntax and semantics) and cognitive abilities (knowledge and reasoning). To systematically evaluate these areas, we developed MM-Eval, a specialized dataset based on Modern Mongolian Language Textbook I and enriched with WebQSP and MGSM datasets. Preliminary experiments on models including Qwen2-7B-Instruct, GLM4-9b-chat, Llama3.1-8B-Instruct, GPT-4, and DeepseekV2.5 revealed that: 1) all models performed better on syntactic tasks than semantic tasks, highlighting a gap in deeper language understanding; and 2) knowledge tasks showed a moderate decline, suggesting that models can transfer general knowledge from high-resource to low-resource contexts. The release of MM-Eval, comprising 569 syntax, 677 semantics, 344 knowledge, and 250 reasoning tasks, offers valuable insights for advancing NLP and LLMs in low-resource languages like Mongolian. The dataset is available at https://github.com/joenahm/MM-Eval.

With the increasing implementation of machine learning models on edge or Internet-of-Things (IoT) devices, deploying advanced models on resource-constrained IoT devices remains challenging. Transformer models, a currently dominant neural architecture, have achieved great success in broad domains but their complexity hinders its deployment on IoT devices with limited computation capability and storage size. Although many model compression approaches have been explored, they often suffer from notorious performance degradation. To address this issue, we introduce a new method, namely Transformer Re-parameterization, to boost the performance of lightweight Transformer models. It consists of two processes: the High-Rank Factorization (HRF) process in the training stage and the deHigh-Rank Factorization (deHRF) process in the inference stage. In the former process, we insert an additional linear layer before the Feed-Forward Network (FFN) of the lightweight Transformer. It is supposed that the inserted HRF layers can enhance the model learning capability. In the later process, the auxiliary HRF layer will be merged together with the following FFN layer into one linear layer and thus recover the original structure of the lightweight model. To examine the effectiveness of the proposed method, we evaluate it on three widely used Transformer variants, i.e., ConvTransformer, Conformer, and SpeechFormer networks, in the application of speech emotion recognition on the IEMOCAP, M3ED and DAIC-WOZ datasets. Experimental results show that our proposed method consistently improves the performance of lightweight Transformers, even making them comparable to large models. The proposed re-parameterization approach enables advanced Transformer models to be deployed on resource-constrained IoT devices.

Our everyday lives now heavily rely on artificial intelligence (AI) powered large language models (LLMs). Like regular users, programmers are also benefiting from the newest large language models. In response to the critical role that AI models play in modern software development, this study presents a thorough evaluation of leading programming assistants, including ChatGPT, Gemini(Bard AI), AlphaCode, and GitHub Copilot. The evaluation is based on tasks like natural language processing and code generation accuracy in different programming languages like Java, Python and C++. Based on the results, it has emphasized their strengths and weaknesses and the importance of further modifications to increase the reliability and accuracy of the latest popular models. Although these AI assistants illustrate a high level of progress in language understanding and code generation, along with ethical considerations and responsible usage, they provoke a necessity for discussion. With time, developing more refined AI technology is essential for achieving advanced solutions in various fields, especially with the knowledge of the feature intricacies of these models and their implications. This study offers a comparison of different LLMs and provides essential feedback on the rapidly changing area of AI models. It also emphasizes the need for ethical developmental practices to actualize AI models' full potential.

Several statistical models for regression of a function $F$ on $\mathbb{R}^d$ without the statistical and computational curse of dimensionality exist, for example by imposing and exploiting geometric assumptions on the distribution of the data (e.g. that its support is low-dimensional), or strong smoothness assumptions on $F$, or a special structure $F$. Among the latter, compositional models assume $F=f\circ g$ with $g$ mapping to $\mathbb{R}^r$ with $r\ll d$, have been studied, and include classical single- and multi-index models and recent works on neural networks. While the case where $g$ is linear is rather well-understood, much less is known when $g$ is nonlinear, and in particular for which $g$'s the curse of dimensionality in estimating $F$, or both $f$ and $g$, may be circumvented. In this paper, we consider a model $F(X):=f(\Pi_\gamma X) $ where $\Pi_\gamma:\mathbb{R}^d\to[0,\rm{len}_\gamma]$ is the closest-point projection onto the parameter of a regular curve $\gamma: [0,\rm{len}_\gamma]\to\mathbb{R}^d$ and $f:[0,\rm{len}_\gamma]\to\mathbb{R}^1$. The input data $X$ is not low-dimensional, far from $\gamma$, conditioned on $\Pi_\gamma(X)$ being well-defined. The distribution of the data, $\gamma$ and $f$ are unknown. This model is a natural nonlinear generalization of the single-index model, which corresponds to $\gamma$ being a line. We propose a nonparametric estimator, based on conditional regression, and show that under suitable assumptions, the strongest of which being that $f$ is coarsely monotone, it can achieve the $one$-$dimensional$ optimal min-max rate for non-parametric regression, up to the level of noise in the observations, and be constructed in time $\mathcal{O}(d^2n\log n)$. All the constants in the learning bounds, in the minimal number of samples required for our bounds to hold, and in the computational complexity are at most low-order polynomials in $d$.

US warships came under sustained missile and drone attack from Houthi fighters as they sailed off the coast of Yemen, the Pentagon has confirmed, with the armed group claiming it attacked the US aircraft carrier Abraham Lincoln and two US destroyers. Pentagon spokesperson Air Force Major General Patrick Ryder said on Tuesday that the United States military's Central Command (CENTCOM) forces "successfully repelled multiple Iranian backed Houthi attacks during a transit of the Bab al-Mandeb strait", which connects the Red Sea to the Gulf of Aden. Ryder told reporters at a news conference that two US-guided missile destroyers – the USS Stockdale and USS Spruance – were attacked by at least eight one-way attack drones, five antiship ballistic missiles and three antiship cruise missiles. All the Houthi drones and missiles "were successfully engaged and defeated", and neither of the US Navy ships were damaged or personnel hurt, he said. Ryder added that he was not aware of any attacks against the aircraft carrier USS Abraham Lincoln.