U.S. Central Command announced Thursday that American aircraft and a coalition warship have shot down six Houthi one-way attack drones in the Red Sea. The unmanned aerial vehicles were identified as "likely targeting U.S. and coalition warships and were an imminent threat," it said, noting that the drones were taken out around 4:30 a.m. "Later, between 8:30 a.m. and 9:45 a.m., the Houthis fired two anti-ship ballistic missiles from southern Yemen into the Gulf of Aden," Central Command also wrote in a post on X. "The missiles impacted MV Islander, a Palau-flagged, U.K.-owned, cargo carrier causing one minor injury and damage. The ship is continuing its voyage." The attack comes after the Pentagon earlier this week confirmed that the Houthis shot down a U.S. MQ-9 Reaper drone off the coast of Yemen on Monday.

The U.S. military conducted "self-defense strikes" against Houthi missiles and a launcher prepared to fire from Yemen toward the Red Sea on Wednesday, U.S. Central Command announced. Between 12 a.m. and 6:45 p.m. local time on Wednesday, four self-defense strikes were launched in response to seven mobile Houthi anti-ship cruise missiles and one mobile anti-ship ballistic missile launcher aimed at the Red Sea, the agency said. Also, in an act of self-defense, CENTCOM said its forces shot down a one-way attack unmanned aircraft system. U.S. Central Command announced more "self-defense strikes" against Houthi terrorists in Yemen after American forces located missiles and a launcher prepared to fire toward the Red Sea. The missiles, launchers and the unmanned aircraft system were all determined to have originated from Houthi-controlled areas of Yemen.

Despite the remarkable abilities of Large Language Models (LLMs) to answer questions, they often display a considerable level of overconfidence even when the question does not have a definitive answer. To avoid providing hallucinated answers to these unknown questions, existing studies typically investigate approaches to refusing to answer these questions. In this work, we propose a novel and scalable self-alignment method to utilize the LLM itself to enhance its response-ability to different types of unknown questions, being capable of not only refusing to answer but also providing explanation to the unanswerability of unknown questions. Specifically, the Self-Align method first employ a two-stage class-aware self-augmentation approach to generate a large amount of unknown question-response data. Then we conduct disparity-driven self-curation to select qualified data for fine-tuning the LLM itself for aligning the responses to unknown questions as desired. Experimental results on two datasets across four types of unknown questions validate the superiority of the Self-Align method over existing baselines in terms of three types of task formulation.

It is of paramount importance to enhance medical practices, given how important it is to protect human life. Medical therapy can be accelerated by automating patient prediction using machine learning techniques. To double the efficiency of classifiers, several preprocessing strategies must be adopted for their crucial duty in this field. Feature selection (FS) is one tool that has been used frequently to modify data and enhance classification outcomes by lowering the dimensionality of datasets. Excluded features are those that have a poor correlation coefficient with the label class, that is, they have no meaningful correlation with classification and do not indicate where the instance belongs. Along with the recurring features, which show a strong association with the remainder of the features. Contrarily, the model being produced during training is harmed, and the classifier is misled by their presence. This causes overfitting and increases algorithm complexity and processing time. These are used in exploration to allow solutions to be found more thoroughly and in relation to a chosen solution than at random. TLSO, PLSO, and LLSO stand for Tournament Logarithmic Snake Optimizer, Proportional Logarithmic Snake Optimizer, and Linear Order Logarithmic Snake Optimizer, respectively. A number of 22 reference medical datasets were used in experiments. The findings indicate that, among 86 % of the datasets, TLSO attained the best accuracy, and among 82 % of the datasets, the best feature reduction. In terms of the standard deviation, the TLSO also attained noteworthy reliability and stability. On the basis of running duration, it is, nonetheless, quite effective.

State-of-the-art pre-trained image models predominantly adopt a two-stage approach: initial unsupervised pre-training on large-scale datasets followed by task-specific fine-tuning using Cross-Entropy loss~(CE). However, it has been demonstrated that CE can compromise model generalization and stability. While recent works employing contrastive learning address some of these limitations by enhancing the quality of embeddings and producing better decision boundaries, they often overlook the importance of hard negative mining and rely on resource intensive and slow training using large sample batches. To counter these issues, we introduce a novel approach named CLCE, which integrates Label-Aware Contrastive Learning with CE. Our approach not only maintains the strengths of both loss functions but also leverages hard negative mining in a synergistic way to enhance performance. Experimental results demonstrate that CLCE significantly outperforms CE in Top-1 accuracy across twelve benchmarks, achieving gains of up to 3.52% in few-shot learning scenarios and 3.41% in transfer learning settings with the BEiT-3 model. Importantly, our proposed CLCE approach effectively mitigates the dependency of contrastive learning on large batch sizes such as 4096 samples per batch, a limitation that has previously constrained the application of contrastive learning in budget-limited hardware environments.

Entity Alignment (EA) is vital for integrating diverse knowledge graph (KG) data, playing a crucial role in data-driven AI applications. Traditional EA methods primarily rely on comparing entity embeddings, but their effectiveness is constrained by the limited input KG data and the capabilities of the representation learning techniques. Against this backdrop, we introduce ChatEA, an innovative framework that incorporates large language models (LLMs) to improve EA. To address the constraints of limited input KG data, ChatEA introduces a KG-code translation module that translates KG structures into a format understandable by LLMs, thereby allowing LLMs to utilize their extensive background knowledge to improve EA accuracy. To overcome the over-reliance on entity embedding comparisons, ChatEA implements a two-stage EA strategy that capitalizes on LLMs' capability for multi-step reasoning in a dialogue format, thereby enhancing accuracy while preserving efficiency. Our experimental results affirm ChatEA's superior performance, highlighting LLMs' potential in facilitating EA tasks.

Lexical Simplification (LS) automatically replaces difficult to read words for easier alternatives while preserving a sentence's original meaning. LS is a precursor to Text Simplification with the aim of improving text accessibility to various target demographics, including children, second language learners, individuals with reading disabilities or low literacy. Several datasets exist for LS. These LS datasets specialize on one or two sub-tasks within the LS pipeline. However, as of this moment, no single LS dataset has been developed that covers all LS sub-tasks. We present MultiLS, the first LS framework that allows for the creation of a multi-task LS dataset. We also present MultiLS-PT, the first dataset to be created using the MultiLS framework. We demonstrate the potential of MultiLS-PT by carrying out all LS sub-tasks of (1). lexical complexity prediction (LCP), (2). substitute generation, and (3). substitute ranking for Portuguese. Model performances are reported, ranging from transformer-based models to more recent large language models (LLMs).

This paper investigates the radioactivity of LLM-generated texts, i.e. whether it is possible to detect that such input was used as training data. Conventional methods like membership inference can carry out this detection with some level of accuracy. We show that watermarked training data leaves traces easier to detect and much more reliable than membership inference. We link the contamination level to the watermark robustness, its proportion in the training set, and the fine-tuning process. We notably demonstrate that training on watermarked synthetic instructions can be detected with high confidence (p-value < 1e-5) even when as little as 5% of training text is watermarked. Thus, LLM watermarking, originally designed for detecting machine-generated text, gives the ability to easily identify if the outputs of a watermarked LLM were used to fine-tune another LLM.

Large Language Models (LLMs) have recently showcased remarkable generalizability in various domains. Despite their extensive knowledge, LLMs still face challenges in efficiently utilizing encoded knowledge to develop accurate and logical reasoning processes. To mitigate this problem, we introduced Hint-before-Solving Prompting (HSP), which guides the model to generate hints (e.g., specific knowledge or key ideas) for solving the problem and then generate solutions containing intermediate reasoning steps. Since HSP is orthogonal to prompting methods (e.g., Chain-of-Thought (CoT)), we applied HSP to CoT, Least-to-Most, Plan-and-Solve, and Standard promptings. The results of extensive experiments on 6 reasoning benchmarks and 4 open-source LLMs demonstrate that HSP can effectively improve the accuracy of reasoning tasks: (1) By applying high-quality hint-enhanced HSP to CoT prompting, Llama2-70B-Chat shows an improvement of 9.7. (2) Beyond exploring training-free LLM capabilities, we built the HSPMATH dataset based on HSP and fine-tuned Llemma-7B, reaching 64.3 accuracy, surpassing GPT-3.5 and WizardMath-13B. We make our code and dataset publicly available at \url{https://github.com/jinlanfu/HSP}.

The present study introduces the knowledge-augmented generator, which is specifically designed to produce information that remains grounded in contextual knowledge, regardless of alterations in the context. Previous research has predominantly focused on examining hallucinations stemming from static input, such as in the domains of summarization or machine translation. However, our investigation delves into the faithfulness of generative question answering in the presence of dynamic knowledge. Our objective is to explore the existence of hallucinations arising from parametric memory when contextual knowledge undergoes changes, while also analyzing the underlying causes for their occurrence. In order to efficiently address this issue, we propose a straightforward yet effective measure for detecting such hallucinations. Intriguingly, our investigation uncovers that all models exhibit a tendency to generate previous answers as hallucinations. To gain deeper insights into the underlying causes of this phenomenon, we conduct a series of experiments that verify the critical role played by context in hallucination, both during training and testing, from various perspectives.