If the Houthis' claims are confirmed, this will have been the second time the group has shot down an American drone since the Oct. 7 Hamas attack on Israel, and Israel's response, plunged the region into crisis. The downing of a Reaper drone, the mainstay of the American military's aerial surveillance fleet, is another escalation of violence between the United States and Iran-backed groups in Yemen, Iraq and Syria. The episodes have intensified over the past two months, underscoring the risk that the conflict between Israel and Hamas could spiral into a wider war. The United States struck five Houthi military targets, including an undersea drone, in Houthi-controlled areas of Yemen on Saturday, according to a statement from the military's Central Command. The use of the underwater drone is believed to have been the first time that the Houthis have employed such a weapon since they began their campaign against ships in the Red Sea and the Gulf of Aden on Oct. 23, the statement said.

Writing formulas on spreadsheets, such as Microsoft Excel and Google Sheets, is a widespread practice among users performing data analysis. However, crafting formulas on spreadsheets remains a tedious and error-prone task for many end-users, particularly when dealing with complex operations. To alleviate the burden associated with writing spreadsheet formulas, this paper introduces a novel benchmark task called NL2Formula, with the aim to generate executable formulas that are grounded on a spreadsheet table, given a Natural Language (NL) query as input. To accomplish this, we construct a comprehensive dataset consisting of 70,799 paired NL queries and corresponding spreadsheet formulas, covering 21,670 tables and 37 types of formula functions. We realize the NL2Formula task by providing a sequence-to-sequence baseline implementation called fCoder. Experimental results validate the effectiveness of fCoder, demonstrating its superior performance compared to the baseline models. Furthermore, we also compare fCoder with an initial GPT-3.5 model (i.e., text-davinci-003). Lastly, through in-depth error analysis, we identify potential challenges in the NL2Formula task and advocate for further investigation.

Large language models (LLMs) have demonstrated impressive abilities in generating unstructured natural language according to instructions. However, their performance can be inconsistent when tasked with producing text that adheres to specific structured formats, which is crucial in applications like named entity recognition (NER) or relation extraction (RE). To address this issue, this paper introduces an efficient method, G&O, to enhance their structured text generation capabilities. It breaks the generation into a two-step pipeline: initially, LLMs generate answers in natural language as intermediate responses. Subsequently, LLMs are asked to organize the output into the desired structure, using the intermediate responses as context. G&O effectively separates the generation of content from the structuring process, reducing the pressure of completing two orthogonal tasks simultaneously. Tested on zero-shot NER and RE, the results indicate a significant improvement in LLM performance with minimal additional efforts. This straightforward and adaptable prompting technique can also be combined with other strategies, like self-consistency, to further elevate LLM capabilities in various structured text generation tasks.

Significant strides have been made in natural language tasks, largely attributed to the emergence of powerful large language models (LLMs). These models, pre-trained on extensive and diverse corpora, have become increasingly capable of comprehending the intricacies of language. Despite the abundance of LLMs for many high-resource languages, the availability of such models remains limited for European Portuguese. We introduce Gl\'orIA, a robust European Portuguese decoder LLM. To pre-train Gl\'orIA, we assembled a comprehensive PT-PT text corpus comprising 35 billion tokens from various sources. We present our pre-training methodology, followed by an assessment of the model's effectiveness on multiple downstream tasks. Additionally, to evaluate our models' language modeling capabilities, we introduce CALAME-PT (Context-Aware LAnguage Modeling Evaluation for Portuguese), the first Portuguese zero-shot language-modeling benchmark. Evaluation shows that Gl\'orIA significantly outperforms existing open PT decoder models in language modeling and that it can generate sound, knowledge-rich, and coherent PT-PT text. The model also exhibits strong potential for various downstream tasks.

Cutting edge techniques developed in the general NLP domain are often subsequently applied to the high-value, data-rich biomedical domain. The past few years have seen generative language models (LMs), instruction finetuning, and few-shot learning become foci of NLP research. As such, generative LMs pretrained on biomedical corpora have proliferated and biomedical instruction finetuning has been attempted as well, all with the hope that domain specificity improves performance on downstream tasks. Given the nontrivial effort in training such models, we investigate what, if any, benefits they have in the key biomedical NLP task of relation extraction. Specifically, we address two questions: (1) Do LMs trained on biomedical corpora outperform those trained on general domain corpora? (2) Do models instruction finetuned on biomedical datasets outperform those finetuned on assorted datasets or those simply pretrained? We tackle these questions using existing LMs, testing across four datasets. In a surprising result, general-domain models typically outperformed biomedical-domain models. However, biomedical instruction finetuning improved performance to a similar degree as general instruction finetuning, despite having orders of magnitude fewer instructions. Our findings suggest it may be more fruitful to focus research effort on larger-scale biomedical instruction finetuning of general LMs over building domain-specific biomedical LMs

We present CFEVER, a Chinese dataset designed for Fact Extraction and VERification. CFEVER comprises 30,012 manually created claims based on content in Chinese Wikipedia. Each claim in CFEVER is labeled as "Supports", "Refutes", or "Not Enough Info" to depict its degree of factualness. Similar to the FEVER dataset, claims in the "Supports" and "Refutes" categories are also annotated with corresponding evidence sentences sourced from single or multiple pages in Chinese Wikipedia. Our labeled dataset holds a Fleiss' kappa value of 0.7934 for five-way inter-annotator agreement. In addition, through the experiments with the state-of-the-art approaches developed on the FEVER dataset and a simple baseline for CFEVER, we demonstrate that our dataset is a new rigorous benchmark for factual extraction and verification, which can be further used for developing automated systems to alleviate human fact-checking efforts. CFEVER is available at https://ikmlab.github.io/CFEVER.

Graph augmentation methods play a crucial role in improving the performance and enhancing generalisation capabilities in Graph Neural Networks (GNNs). Existing graph augmentation methods mainly perturb the graph structures and are usually limited to pairwise node relations. These methods cannot fully address the complexities of real-world large-scale networks that often involve higher-order node relations beyond only being pairwise. Meanwhile, real-world graph datasets are predominantly modelled as simple graphs, due to the scarcity of data that can be used to form higher-order edges. Therefore, reconfiguring the higher-order edges as an integration into graph augmentation strategies lights up a promising research path to address the aforementioned issues. In this paper, we present Hyperedge Augmentation (HyperAug), a novel graph augmentation method that constructs virtual hyperedges directly form the raw data, and produces auxiliary node features by extracting from the virtual hyperedge information, which are used for enhancing GNN performances on downstream tasks. We design three diverse virtual hyperedge construction strategies to accompany the augmentation scheme: (1) via graph statistics, (2) from multiple data perspectives, and (3) utilising multi-modality. Furthermore, to facilitate HyperAug evaluation, we provide 23 novel real-world graph datasets across various domains including social media, biology, and e-commerce. Our empirical study shows that HyperAug consistently and significantly outperforms GNN baselines and other graph augmentation methods, across a variety of application contexts, which clearly indicates that it can effectively incorporate higher-order node relations into graph augmentation methods for real-world complex networks.

Risk mitigation techniques are critical to avoiding accidents associated with driving behaviour. We provide a novel Multi-Class Driver Distraction Risk Assessment (MDDRA) model that considers the vehicle, driver, and environmental data during a journey. MDDRA categorises the driver on a risk matrix as safe, careless, or dangerous. It offers flexibility in adjusting the parameters and weights to consider each event on a specific severity level. We collect real-world data using the Field Operation Test (TeleFOT), covering drivers using the same routes in the East Midlands, United Kingdom (UK). The results show that reducing road accidents caused by driver distraction is possible. We also study the correlation between distraction (driver, vehicle, and environment) and the classification severity based on a continuous distraction severity score. Furthermore, we apply machine learning techniques to classify and predict driver distraction according to severity levels to aid the transition of control from the driver to the vehicle (vehicle takeover) when a situation is deemed risky. The Ensemble Bagged Trees algorithm performed best, with an accuracy of 96.2%.

Understanding how Transformer-based Language Models (LMs) learn and recall information is a key goal of the deep learning community. Recent interpretability methods project weights and hidden states obtained from the forward pass to the models' vocabularies, helping to uncover how information flows within LMs. In this work, we extend this methodology to LMs' backward pass and gradients. We first prove that a gradient matrix can be cast as a low-rank linear combination of its forward and backward passes' inputs. We then develop methods to project these gradients into vocabulary Figure 1: An illustration depicting the tokens promoted items and explore the mechanics of how by a single LM's MLP layer and its gradient during the new information is stored in the LMs' neurons.

Entity Linking (EL) is an essential and challenging task in natural language processing that seeks to link some text representing an entity within a document or sentence with its corresponding entry in a dictionary or knowledge base. Most existing approaches focus on creating elaborate contextual models that look for clues the words surrounding the entity-text to help solve the linking problem. Although these fine-tuned language models tend to work, they can be unwieldy, difficult to train, and do not transfer well to other domains. Fortunately, Large Language Models (LLMs) like GPT provide a highly-advanced solution to the problems inherent in EL models, but simply naive prompts to LLMs do not work well. In the present work, we define ChatEL, which is a three-step framework to prompt LLMs to return accurate results. Overall the ChatEL framework improves the average F1 performance across 10 datasets by more than 2%. Finally, a thorough error analysis shows many instances with the ground truth labels were actually incorrect, and the labels predicted by ChatEL were actually correct. This indicates that the quantitative results presented in this paper may be a conservative estimate of the actual performance.