Knowledge probing assesses to which degree a language model (LM) has successfully learned relational knowledge during pre-training. Probing is an inexpensive way to compare LMs of different sizes and training configurations. However, previous approaches rely on the objective function used in pre-training LMs and are thus applicable only to masked or causal LMs. As a result, comparing different types of LMs becomes impossible. To address this, we propose an approach that uses an LM's inherent ability to estimate the log-likelihood of any given textual statement. We carefully design an evaluation dataset of 7,731 instances (40,916 in a larger variant) from which we produce alternative statements for each relational fact, one of which is correct. We then evaluate whether an LM correctly assigns the highest log-likelihood to the correct statement. Our experimental evaluation of 22 common LMs shows that our proposed framework, BEAR, can effectively probe for knowledge across different LM types. We release the BEAR datasets and an open-source framework that implements the probing approach to the research community to facilitate the evaluation and development of LMs.

High-dimensional longitudinal time series data is prevalent across various real-world applications. Many such applications can be modeled as regression problems with high-dimensional time series covariates. Deep learning has been a popular and powerful tool for fitting these regression models. Yet, the development of interpretable and reproducible deep-learning models is challenging and remains underexplored. This study introduces a novel method, Deep Learning Inference using Knockoffs for Time series data (DeepLINK-T), focusing on the selection of significant time series variables in regression while controlling the false discovery rate (FDR) at a predetermined level. DeepLINK-T combines deep learning with knockoff inference to control FDR in feature selection for time series models, accommodating a wide variety of feature distributions. It addresses dependencies across time and features by leveraging a time-varying latent factor structure in time series covariates. Three key ingredients for DeepLINK-T are 1) a Long Short-Term Memory (LSTM) autoencoder for generating time series knockoff variables, 2) an LSTM prediction network using both original and knockoff variables, and 3) the application of the knockoffs framework for variable selection with FDR control. Extensive simulation studies have been conducted to evaluate DeepLINK-T's performance, showing its capability to control FDR effectively while demonstrating superior feature selection power for high-dimensional longitudinal time series data compared to its non-time series counterpart. DeepLINK-T is further applied to three metagenomic data sets, validating its practical utility and effectiveness, and underscoring its potential in real-world applications.

Anomaly detection in wind turbines typically involves using normal behaviour models to detect faults early. However, training autoencoder models for each turbine is time-consuming and resource intensive. Thus, transfer learning becomes essential for wind turbines with limited data or applications with limited computational resources. This study examines how cross-turbine transfer learning can be applied to autoencoder-based anomaly detection. Here, autoencoders are combined with constant thresholds for the reconstruction error to determine if input data contains an anomaly. The models are initially trained on one year's worth of data from one or more source wind turbines. They are then fine-tuned using smaller amounts of data from another turbine. Three methods for fine-tuning are investigated: adjusting the entire autoencoder, only the decoder, or only the threshold of the model. The performance of the transfer learning models is compared to baseline models that were trained on one year's worth of data from the target wind turbine. The results of the tests conducted in this study indicate that models trained on data of multiple wind turbines do not improve the anomaly detection capability compared to models trained on data of one source wind turbine. In addition, modifying the model's threshold can lead to comparable or even superior performance compared to the baseline, whereas fine-tuning the decoder or autoencoder further enhances the models' performance.

Large language models (LLMs) often generate content that contains factual errors when responding to fact-seeking prompts on open-ended topics. To benchmark a model's long-form factuality in open domains, we first use GPT-4 to generate LongFact, a prompt set comprising thousands of questions spanning 38 topics. We then propose that LLM agents can be used as automated evaluators for long-form factuality through a method which we call Search-Augmented Factuality Evaluator (SAFE). SAFE utilizes an LLM to break down a long-form response into a set of individual facts and to evaluate the accuracy of each fact using a multi-step reasoning process comprising sending search queries to Google Search and determining whether a fact is supported by the search results. Furthermore, we propose extending F1 score as an aggregated metric for long-form factuality. To do so, we balance the percentage of supported facts in a response (precision) with the percentage of provided facts relative to a hyperparameter representing a user's preferred response length (recall). Empirically, we demonstrate that LLM agents can outperform crowdsourced human annotators - on a set of ~16k individual facts, SAFE agrees with crowdsourced human annotators 72% of the time, and on a random subset of 100 disagreement cases, SAFE wins 76% of the time. At the same time, SAFE is more than 20 times cheaper than human annotators. We also benchmark thirteen language models on LongFact across four model families (Gemini, GPT, Claude, and PaLM-2), finding that larger language models generally achieve better long-form factuality. LongFact, SAFE, and all experimental code are available at https://github.com/google-deepmind/long-form-factuality.

Video captures the moment and aftermath of what appears to be a drone, allegedly of Ukrainian origin, striking Russian drone production facility. Russian officials claimed that only a worker's dormitory was hit. A Ukrainian "plane-type UAV" on Tuesday struck a Russian weapons plant that allegedly assembled drones, causing an incredible fireball after impact. "This morning, the republic's industrial enterprises in Yelabuga and Nizhnekamsk were attacked by drones," Rustam Minnikhanov, the leader of Russia's autonomous Republic of Tatarstan, said in a post on his Telegram channel. "There is no serious damage, the technological process of the enterprises was not disrupted," Minnikhanov added.

Practitioners commonly download pretrained machine learning models from open repositories and finetune them to fit specific applications. We show that this practice introduces a new risk of privacy backdoors. By tampering with a pretrained model's weights, an attacker can fully compromise the privacy of the finetuning data. We show how to build privacy backdoors for a variety of models, including transformers, which enable an attacker to reconstruct individual finetuning samples, with a guaranteed success! We further show that backdoored models allow for tight privacy attacks on models trained with differential privacy (DP). The common optimistic practice of training DP models with loose privacy guarantees is thus insecure if the model is not trusted. Overall, our work highlights a crucial and overlooked supply chain attack on machine learning privacy.

Conceptual reasoning, the ability to reason in abstract and high-level perspectives, is key to generalization in human cognition. However, limited study has been done on large language models' capability to perform conceptual reasoning. In this work, we bridge this gap and propose a novel conceptualization framework that forces models to perform conceptual reasoning on abstract questions and generate solutions in a verifiable symbolic space. Using this framework as an analytical tool, we show that existing large language models fall short on conceptual reasoning, dropping 9% to 28% on various benchmarks compared to direct inference methods. We then discuss how models can improve since high-level abstract reasoning is key to unbiased and generalizable decision-making. We propose two techniques to add trustworthy induction signals by generating familiar questions with similar underlying reasoning paths and asking models to perform self-refinement. Experiments show that our proposed techniques improve models' conceptual reasoning performance by 8% to 11%, achieving a more robust reasoning system that relies less on inductive biases.

This paper presents a collection of highly comparable web corpora of Slovenian, Croatian, Bosnian, Montenegrin, Serbian, Macedonian, and Bulgarian, covering thereby the whole spectrum of official languages in the South Slavic language space. The collection of these corpora comprises a total of 13 billion tokens of texts from 26 million documents. The comparability of the corpora is ensured by a comparable crawling setup and the usage of identical crawling and post-processing technology. All the corpora were linguistically annotated with the state-of-the-art CLASSLA-Stanza linguistic processing pipeline, and enriched with document-level genre information via the Transformer-based multilingual X-GENRE classifier, which further enhances comparability at the level of linguistic annotation and metadata enrichment. The genre-focused analysis of the resulting corpora shows a rather consistent distribution of genres throughout the seven corpora, with variations in the most prominent genre categories being well-explained by the economic strength of each language community. A comparison of the distribution of genre categories across the corpora indicates that web corpora from less developed countries primarily consist of news articles.

Deep learning techniques have been explored within the marine litter problem for approximately 20 years but the majority of the research has developed rapidly in the last five years. We provide an in-depth, up to date, summary and analysis of 28 of the most recent and significant contributions of deep learning in marine debris. From cross referencing the research paper results, the YOLO family significantly outperforms all other methods of object detection but there are many respected contributions to this field that have categorically agreed that a comprehensive database of underwater debris is not currently available for machine learning. Using a small dataset curated and labelled by us, we tested YOLOv5 on a binary classification task and found the accuracy was low and the rate of false positives was high; highlighting the importance of a comprehensive database. We conclude this survey with over 40 future research recommendations and open challenges.

Large-scale high-resolution (HR) land-cover mapping is a vital task to survey the Earth's surface and resolve many challenges facing humanity. However, it is still a non-trivial task hindered by complex ground details, various landforms, and the scarcity of accurate training labels over a wide-span geographic area. In this paper, we propose an efficient, weakly supervised framework (Paraformer) to guide large-scale HR land-cover mapping with easy-access historical land-cover data of low resolution (LR). Specifically, existing land-cover mapping approaches reveal the dominance of CNNs in preserving local ground details but still suffer from insufficient global modeling in various landforms. Therefore, we design a parallel CNN-Transformer feature extractor in Paraformer, consisting of a downsampling-free CNN branch and a Transformer branch, to jointly capture local and global contextual information. Besides, facing the spatial mismatch of training data, a pseudo-label-assisted training (PLAT) module is adopted to reasonably refine LR labels for weakly supervised semantic segmentation of HR images. Experiments on two large-scale datasets demonstrate the superiority of Paraformer over other state-of-the-art methods for automatically updating HR land-cover maps from LR historical labels.