The expanding financial markets of the Arab world require sophisticated Arabic NLP tools. To address this need within the banking domain, the Arabic Financial NLP (AraFinNLP) shared task proposes two subtasks: (i) Multi-dialect Intent Detection and (ii) Cross-dialect Translation and Intent Preservation. This shared task uses the updated ArBanking77 dataset, which includes about 39k parallel queries in MSA and four dialects. Each query is labeled with one or more of a common 77 intents in the banking domain. These resources aim to foster the development of robust financial Arabic NLP, particularly in the areas of machine translation and banking chat-bots. A total of 45 unique teams registered for this shared task, with 11 of them actively participated in the test phase. Specifically, 11 teams participated in Subtask 1, while only 1 team participated in Subtask 2. The winning team of Subtask 1 achieved F1 score of 0.8773, and the only team submitted in Subtask 2 achieved a 1.667 BLEU score.

Scaling model capacity enhances its capabilities but significantly increases computation. Mixture-of-Experts models (MoEs) address this by allowing model capacity to scale without substantially increasing training or inference costs. Despite their promising results, MoE models encounter several challenges. Primarily, the dispersion of training tokens across multiple experts can lead to underfitting, particularly for infrequent tokens. Additionally, while fixed routing mechanisms can mitigate this issue, they compromise on the diversity of representations. In this paper, we propose MaskMoE, a method designed to enhance token-level learning by employing a routing masking technique within the Mixture-of-Experts model. MaskMoE is capable of maintaining representation diversity while achieving more comprehensive training. Experimental results demonstrate that our method outperforms previous dominant Mixture-of-Experts models in both perplexity (PPL) and downstream tasks.

We propose a computationally efficient algorithm for gradient-based linear dimension reduction and high-dimensional regression. The algorithm initially computes a Mondrian forest and uses this estimator to identify a relevant feature subspace of the inputs from an estimate of the expected gradient outer product (EGOP) of the regression function. In addition, we introduce an iterative approach known as Transformed Iterative Mondrian (TrIM) forest to improve the Mondrian forest estimator by using the EGOP estimate to update the set of features and weights used by the Mondrian partitioning mechanism. We obtain consistency guarantees and convergence rates for the estimation of the EGOP matrix and the random forest estimator obtained from one iteration of the TrIM algorithm. Lastly, we demonstrate the effectiveness of our proposed algorithm for learning the relevant feature subspace across a variety of settings with both simulated and real data.

Prime Minister Fumio Kishida and new British Prime Minister Keir Starmer agreed on Thursday to boost cooperation between their countries in a wide range of fields including artificial intelligence. In their first in-person talks, held in Washington, the two leaders also confirmed that the security of the Euro-Atlantic and Indo-Pacific regions are inseparable. Kishida on July 6 had telephone talks with Starmer, who led his party to a landslide general election victory on July 4. They also agreed to promote the joint development of the next-generation fighter jet involving their countries plus Italy and discussed the situations in the Middle East and East Asia, including North Korea, and affirmed their close collaboration. Separately, Kishida met with new Dutch Prime Minister Dick Schoof and congratulated him on his inauguration.

To build large language models for Ukrainian we need to expand our corpora with large amounts of new algorithmic tasks expressed in natural language. Examples of task performance expressed in English are abundant, so with a high-quality translation system our community will be enabled to curate datasets faster. To aid this goal, we introduce a recipe to build a translation system using supervised finetuning of a large pretrained language model with a noisy parallel dataset of 3M pairs of Ukrainian and English sentences followed by a second phase of training using 17K examples selected by k-fold perplexity filtering on another dataset of higher quality. Our decoder-only model named Dragoman beats performance of previous state of the art encoder-decoder models on the FLORES devtest set.

Model evaluations are central to understanding the safety, risks, and societal impacts of AI systems. While most real-world AI applications involve human-AI interaction, most current evaluations (e.g., common benchmarks) of AI models do not. Instead, they incorporate human factors in limited ways, assessing the safety of models in isolation, thereby falling short of capturing the complexity of human-model interactions. In this paper, we discuss and operationalize a definition of an emerging category of evaluations -- "human interaction evaluations" (HIEs) -- which focus on the assessment of human-model interactions or the process and the outcomes of humans using models. First, we argue that HIEs can be used to increase the validity of safety evaluations, assess direct human impact and interaction-specific harms, and guide future assessments of models' societal impact. Second, we propose a safety-focused HIE design framework -- containing a human-LLM interaction taxonomy -- with three stages: (1) identifying the risk or harm area, (2) characterizing the use context, and (3) choosing the evaluation parameters. Third, we apply our framework to two potential evaluations for overreliance and persuasion risks. Finally, we conclude with tangible recommendations for addressing concerns over costs, replicability, and unrepresentativeness of HIEs.

In this survey we are focusing on utilizing drone-based systems for the detection of individuals, particularly by identifying human screams and other distress signals. This study has significant relevance in post-disaster scenarios, including events such as earthquakes, hurricanes, military conflicts, wildfires, and more. These drones are capable of hovering over disaster-stricken areas that may be challenging for rescue teams to access directly. Unmanned aerial vehicles (UAVs), commonly referred to as drones, are frequently deployed for search-and-rescue missions during disaster situations. Typically, drones capture aerial images to assess structural damage and identify the extent of the disaster. They also employ thermal imaging technology to detect body heat signatures, which can help locate individuals. In some cases, larger drones are used to deliver essential supplies to people stranded in isolated disaster-stricken areas. In our discussions, we delve into the unique challenges associated with locating humans through aerial acoustics. The auditory system must distinguish between human cries and sounds that occur naturally, such as animal calls and wind. Additionally, it should be capable of recognizing distinct patterns related to signals like shouting, clapping, or other ways in which people attempt to signal rescue teams. To tackle this challenge, one solution involves harnessing artificial intelligence (AI) to analyze sound frequencies and identify common audio signatures. Deep learning-based networks, such as convolutional neural networks (CNNs), can be trained using these signatures to filter out noise generated by drone motors and other environmental factors. Furthermore, employing signal processing techniques like the direction of arrival (DOA) based on microphone array signals can enhance the precision of tracking the source of human noises.

Instruction-tuned Large Language Models (LLMs) can perform a wide range of tasks given natural language instructions to do so, but they are sensitive to how such instructions are phrased. This issue is especially concerning in healthcare, as clinicians are unlikely to be experienced prompt engineers and the potential consequences of inaccurate outputs are heightened in this domain. This raises a practical question: How robust are instruction-tuned LLMs to natural variations in the instructions provided for clinical NLP tasks? We collect prompts from medical doctors across a range of tasks and quantify the sensitivity of seven LLMs -- some general, others specialized -- to natural (i.e., non-adversarial) instruction phrasings. We find that performance varies substantially across all models, and that -- perhaps surprisingly -- domain-specific models explicitly trained on clinical data are especially brittle, compared to their general domain counterparts. Further, arbitrary phrasing differences can affect fairness, e.g., valid but distinct instructions for mortality prediction yield a range both in overall performance, and in terms of differences between demographic groups.

Image-text interleaved data, consisting of multiple images and texts arranged in a natural document format, aligns with the presentation paradigm of internet data and closely resembles human reading habits. Recent studies have shown that such data aids multimodal in-context learning and maintains the capabilities of large language models during multimodal fine-tuning. However, the limited scale and diversity of current image-text interleaved data restrict the development of multimodal large language models. In this paper, we introduce OmniCorpus, a 10 billion-level image-text interleaved dataset. Using an efficient data engine, we filter and extract large-scale high-quality documents, which contain 8.6 billion images and 1,696 billion text tokens. Compared to counterparts (e.g., MMC4, OBELICS), our dataset 1) has 15 times larger scales while maintaining good data quality; 2) features more diverse sources, including both English and non-English websites as well as video-centric websites; 3) is more flexible, easily degradable from an image-text interleaved format to pure text corpus and image-text pairs. Through comprehensive analysis and experiments, we validate the quality, usability, and effectiveness of the proposed dataset. We hope this could provide a solid data foundation for future multimodal model research.

We present ACME: A Chatbot for asylum-seeking Migrants tool that goes beyond the checklists used for handling well-defined, in Europe. ACME relies on computational argumentation and simple procedures since there is not only a problem of evaluating aims to help migrants identify the highest level of protection they legal and factual data, but there is also an issue with understanding can apply for. This would contribute to a more sustainable migration which procedures are relevant. Indeed, there is not only one type of by reducing the load on territorial commissions, Courts, and humanitarian protection but several ones. Importantly, since applicants may be political organizations supporting asylum applicants. We describe the refugees and victims of abuse, discrimination, and persecution, context, system architectures, technologies, and the case study used the collection and processing of their personal data for immigration to run the demonstration.