How can large language models (LLMs) process and translate endangered languages? Many languages lack a large corpus to train a decent LLM; therefore existing LLMs rarely perform well in unseen, endangered languages. On the contrary, we observe that 2000 endangered languages, though without a large corpus, have a grammar book or a dictionary. We propose LINGOLLM, a training-free approach to enable an LLM to process unseen languages that hardly occur in its pre-training. Our key insight is to demonstrate linguistic knowledge of an unseen language in an LLM's prompt, including a dictionary, a grammar book, and morphologically analyzed input text. We implement LINGOLLM on top of two models, GPT-4 and Mixtral, and evaluate their performance on 5 tasks across 8 endangered or low-resource languages. Our results show that LINGOLLM elevates translation capability from GPT-4's 0 to 10.5 BLEU for 10 language directions. Our findings demonstrate the tremendous value of linguistic knowledge in the age of LLMs for endangered languages. Our data, code, and model generations can be found at https://github.com/LLiLab/llm4endangeredlang.

We study existing approaches to leverage off-the-shelf Natural Language Inference (NLI) models for the evaluation of summary faithfulness and argue that these are sub-optimal due to the granularity level considered for premises and hypotheses. That is, the smaller content unit considered as hypothesis is a sentence and premises are made up of a fixed number of document sentences. We propose a novel approach, namely InFusE, that uses a variable premise size and simplifies summary sentences into shorter hypotheses. Departing from previous studies which focus on single short document summarisation, we analyse NLI based faithfulness evaluation for diverse summarisation tasks. We introduce DiverSumm, a new benchmark comprising long form summarisation (long documents and summaries) and diverse summarisation tasks (e.g., meeting and multi-document summarisation). In experiments, InFusE obtains superior performance across the different summarisation tasks. Our code and data are available at https://github.com/HJZnlp/infuse.

There is a large volume of late antique and medieval Hebrew texts. They represent a crucial linguistic and cultural bridge between Biblical and modern Hebrew. Poetry is prominent in these texts and one of its main haracteristics is the frequent use of metaphor. Distinguishing figurative and literal language use is a major task for scholars of the Humanities, especially in the fields of literature, linguistics, and hermeneutics. This paper presents a new, challenging dataset of late antique and medieval Hebrew poetry with expert annotations of metaphor, as well as some baseline results, which we hope will facilitate further research in this area.

Retinal images and vasculature reflect the body's micro-and macrovascular health. They can be used to diagnose DM complications, including diabetic retinopathy (DR), neuropathy, nephropathy, and atherosclerotic cardiovascular disease, as well as forecast the risk of cardiovascular events. Artificial intelligence (AI)-enabled systems developed for high-throughput detection of DR using digitized retinal images have become clinically adopted. Beyond DR screening, AI integration also holds immense potential to address challenges associated with the holistic care of the patient with DM. In this work, we aim to comprehensively review the literature for studies on AI applications based on retinal images related to DM diagnosis, prognostication, and management. We will describe the findings of holistic AI-assisted diabetes care, including but not limited to DR screening, and discuss barriers to implementing such systems, including issues concerning ethics, data privacy, equitable access, and explainability. With the ability to evaluate the patient's health status vis a vis DM complication as well as risk prognostication of future cardiovascular complications, AIassisted retinal image analysis has the potential to become a central tool for modern personalized medicine in patients with DM.

Individual neurons participate in the representation of multiple high-level concepts. To what extent can different interpretability methods successfully disentangle these roles? To help address this question, we introduce RAVEL (Resolving Attribute-Value Entanglements in Language Models), a dataset that enables tightly controlled, quantitative comparisons between a variety of existing interpretability methods. We use the resulting conceptual framework to define the new method of Multi-task Distributed Alignment Search (MDAS), which allows us to find distributed representations satisfying multiple causal criteria. With Llama2-7B as the target language model, MDAS achieves state-of-the-art results on RAVEL, demonstrating the importance of going beyond neuron-level analyses to identify features distributed across activations. We release our benchmark at https://github.com/explanare/ravel.

We study how to characterize and predict the truthfulness of texts generated from large language models (LLMs), which serves as a crucial step in building trust between humans and LLMs. Although several approaches based on entropy or verbalized uncertainty have been proposed to calibrate model predictions, these methods are often intractable, sensitive to hyperparameters, and less reliable when applied in generative tasks with LLMs. In this paper, we suggest investigating internal activations and quantifying LLM's truthfulness using the local intrinsic dimension (LID) of model activations. Through experiments on four question answering (QA) datasets, we demonstrate the effectiveness ohttps://info.arxiv.org/help/prep#abstractsf our proposed method. Additionally, we study intrinsic dimensions in LLMs and their relations with model layers, autoregressive language modeling, and the training of LLMs, revealing that intrinsic dimensions can be a powerful approach to understanding LLMs.

Deep Learning is the state-of-the-art technology for segmenting brain tumours. However, this requires a lot of high-quality data, which is difficult to obtain, especially in the medical field. Therefore, our solutions address this problem by using unconventional mechanisms for data augmentation. Generative adversarial networks and registration are used to massively increase the amount of available samples for training three different deep learning models for brain tumour segmentation, the first task of the BraTS2023 challenge. The first model is the standard nnU-Net, the second is the Swin UNETR and the third is the winning solution of the BraTS 2021 Challenge. The entire pipeline is built on the nnU-Net implementation, except for the generation of the synthetic data. The use of convolutional algorithms and transformers is able to fill each other's knowledge gaps. Using the new metric, our best solution achieves the dice results 0.9005, 0.8673, 0.8509 and HD95 14.940, 14.467, 17.699 (whole tumour, tumour core and enhancing tumour) in the validation set.

Due to the excellent capacities of large language models (LLMs), it becomes feasible to develop LLM-based agents for reliable user simulation. Considering the scarcity and limit (e.g., privacy issues) of real user data, in this paper, we conduct large-scale user simulation for web search, to improve the analysis and modeling of user search behavior. Specially, we propose BASES, a novel user simulation framework with LLM-based agents, designed to facilitate comprehensive simulations of web search user behaviors. Our simulation framework can generate unique user profiles at scale, which subsequently leads to diverse search behaviors. To demonstrate the effectiveness of BASES, we conduct evaluation experiments based on two human benchmarks in both Chinese and English, demonstrating that BASES can effectively simulate large-scale human-like search behaviors. To further accommodate the research on web search, we develop WARRIORS, a new large-scale dataset encompassing web search user behaviors, including both Chinese and English versions, which can greatly bolster research in the field of information retrieval. Our code and data will be publicly released soon.

Defending signal communication from attackers is a fundamental problem in information theory (Karlof This paper explores a scenario in which a malicious and Wagner, 2003; Perrig et al., 2004). Notably, some actor employs a multi-armed attack attacks are aimed at the physical layer of the communication strategy to manipulate data samples, offering channel, which is responsible for transmitting them various avenues to introduce noise the signal. The goal of such attacks is to generate into the dataset. Our central objective is a denial of service (DoS), which involves disrupting to protect the data by detecting any alterations legitimate communication by causing intentional malfunction to the input. We approach this defensive of the communication channel (Grover et al., strategy with utmost caution, operating 2014). In a typical input perturbation scenario, a malicious in an environment where the defender possesses actor is allowed to detect and alter the signal significantly less information compared before it reaches the communication channel (Sadeghi to the attacker. Specifically, the defender is and Larsson, 2019; Tian et al., 2022). The interest in unable to utilize any data samples for training such attacks has been exacerbated by the growing popularity a defense model or verifying the integrity of machine learning (ML) models, which are of the channel. Instead, the defender relies known to be vulnerable to adversarial attacks (Goodfellow exclusively on a set of pre-existing detectors et al., 2014).

Trapped human detection in search and rescue (SAR) scenarios poses a significant challenge in pervasive computing. This study addresses this issue by leveraging machine learning techniques, given their high accuracy. However, accurate identification of trapped individuals is hindered by the curse of dimensionality and noisy data. Particularly in non-line-of-sight (NLOS) situations during catastrophic events, the curse of dimensionality may lead to blind spots due to noise and uncorrelated values in detections. This research focuses on harmonizing information through wireless communication and identifying individuals in NLOS scenarios using ultra-wideband (UWB) radar signals. Employing independent component analysis (ICA) for feature extraction, the study evaluates classification performance using ensemble algorithms on both static and dynamic datasets. The experimental results demonstrate categorization accuracies of 88.37% for static data and 87.20% for dynamic data, highlighting the effectiveness of the proposed approach. Finally, this work can help scientists and engineers make instant decisions during SAR operations.