Large Language Models (LLMs) are capable of performing zero-shot closed-book question answering tasks, based on their internal knowledge stored in parameters during pre-training. However, such internalized knowledge might be insufficient and incorrect, which could lead LLMs to generate factually wrong answers. Furthermore, fine-tuning LLMs to update their knowledge is expensive. To this end, we propose to augment the knowledge directly in the input of LLMs. Specifically, we first retrieve the relevant facts to the input question from the knowledge graph based on semantic similarities between the question and its associated facts. After that, we prepend the retrieved facts to the input question in the form of the prompt, which is then forwarded to LLMs to generate the answer. Our framework, Knowledge-Augmented language model PromptING (KAPING), requires no model training, thus completely zero-shot. We validate the performance of our KAPING framework on the knowledge graph question answering task, that aims to answer the user's question based on facts over a knowledge graph, on which ours outperforms relevant zero-shot baselines by up to 48% in average, across multiple LLMs of various sizes.

The need to compactly and robustly represent item-attribute relations arises in many important tasks, such as faceted browsing and recommendation systems. A popular machine learning approach for this task denotes that an item has an attribute by a high dot-product between vectors for the item and attribute -- a representation that is not only dense, but also tends to correct noisy and incomplete data. While this method works well for queries retrieving items by a single attribute (such as \emph{movies that are comedies}), we find that vector embeddings do not so accurately support compositional queries (such as movies that are comedies and British but not romances). To address these set-theoretic compositions, this paper proposes to replace vectors with box embeddings, a region-based representation that can be thought of as learnable Venn diagrams. We introduce a new benchmark dataset for compositional queries, and present experiments and analysis providing insights into the behavior of both. We find that, while vector and box embeddings are equally suited to single attribute queries, for compositional queries box embeddings provide substantial advantages over vectors, particularly at the moderate and larger retrieval set sizes that are most useful for users' search and browsing.

Much recent effort has been devoted to creating large-scale language models. Nowadays, the most prominent approaches are based on deep neural networks, such as BERT. However, they lack transparency and interpretability, and are often seen as black boxes. This affects not only their applicability in downstream tasks but also the comparability of different architectures or even of the same model trained using different corpora or hyperparameters. In this paper, we propose a set of intrinsic evaluation tasks that inspect the linguistic information encoded in models developed for Brazilian Portuguese. These tasks are designed to evaluate how different language models generalise information related to grammatical structures and multiword expressions (MWEs), thus allowing for an assessment of whether the model has learned different linguistic phenomena. The dataset that was developed for these tasks is composed of a series of sentences with a single masked word and a cue phrase that helps in narrowing down the context. This dataset is divided into MWEs and grammatical structures, and the latter is subdivided into 6 tasks: impersonal verbs, subject agreement, verb agreement, nominal agreement, passive and connectors. The subset for MWEs was used to test BERTimbau Large, BERTimbau Base and mBERT. For the grammatical structures, we used only BERTimbau Large, because it yielded the best results in the MWE task.

Machine learning models that convert user-written text descriptions into images are now widely available online and used by millions of users to generate millions of images a day. We investigate the potential for these models to amplify dangerous and complex stereotypes. We find a broad range of ordinary prompts produce stereotypes, including prompts simply mentioning traits, descriptors, occupations, or objects. For example, we find cases of prompting for basic traits or social roles resulting in images reinforcing whiteness as ideal, prompting for occupations resulting in amplification of racial and gender disparities, and prompting for objects resulting in reification of American norms. Stereotypes are present regardless of whether prompts explicitly mention identity and demographic language or avoid such language. Moreover, stereotypes persist despite mitigation strategies; neither user attempts to counter stereotypes by requesting images with specific counter-stereotypes nor institutional attempts to add system ``guardrails'' have prevented the perpetuation of stereotypes. Our analysis justifies concerns regarding the impacts of today's models, presenting striking exemplars, and connecting these findings with deep insights into harms drawn from social scientific and humanist disciplines. This work contributes to the effort to shed light on the uniquely complex biases in language-vision models and demonstrates the ways that the mass deployment of text-to-image generation models results in mass dissemination of stereotypes and resulting harms.

We have recently witnessed a number of impressive results on hard mathematical reasoning problems with language models. At the same time, the robustness of these models has also been called into question; recent works have shown that models can rely on shallow patterns in the problem description when generating a solution. Building on the idea of behavioral testing, we propose a novel framework, which pins down the causal effect of various factors in the input, e.g., the surface form of the problem text, the operands, and math operators on the output solution. By grounding the behavioral analysis in a causal graph describing an intuitive reasoning process, we study the behavior of language models in terms of robustness and sensitivity to direct interventions in the input space. We apply our framework on a test bed of math word problems. Our analysis shows that robustness does not appear to continuously improve as a function of size, but the GPT-3 Davinci models (175B) achieve a dramatic improvement in both robustness and sensitivity compared to all other GPT variants.

Processing information locked within clinical health records is a challenging task that remains an active area of research in biomedical NLP. In this work, we evaluate a broad set of machine learning techniques ranging from simple RNNs to specialised transformers such as BioBERT on a dataset containing clinical notes along with a set of annotations indicating whether a sample is cancer-related or not. Furthermore, we specifically employ efficient fine-tuning methods from NLP, namely, bottleneck adapters and prompt tuning, to adapt the models to our specialised task. Our evaluations suggest that fine-tuning a frozen BERT model pre-trained on natural language and with bottleneck adapters outperforms all other strategies, including full fine-tuning of the specialised BioBERT model. Based on our findings, we suggest that using bottleneck adapters in low-resource situations with limited access to labelled data or processing capacity could be a viable strategy in biomedical text mining. The code used in the experiments are going to be made available at https://github.com/omidrohanian/bottleneck-adapters.

The COVID-19 pandemic has posed a heavy burden to the healthcare system worldwide and caused huge social disruption and economic loss. Many deep learning models have been proposed to conduct clinical predictive tasks such as mortality prediction for COVID-19 patients in intensive care units using Electronic Health Record (EHR) data. Despite their initial success in certain clinical applications, there is currently a lack of benchmarking results to achieve a fair comparison so that we can select the optimal model for clinical use. Furthermore, there is a discrepancy between the formulation of traditional prediction tasks and real-world clinical practice in intensive care. To fill these gaps, we propose two clinical prediction tasks, Outcome-specific length-of-stay prediction and Early mortality prediction for COVID-19 patients in intensive care units. The two tasks are adapted from the naive length-of-stay and mortality prediction tasks to accommodate the clinical practice for COVID-19 patients. We propose fair, detailed, open-source data-preprocessing pipelines and evaluate 17 state-of-the-art predictive models on two tasks, including 5 machine learning models, 6 basic deep learning models and 6 deep learning predictive models specifically designed for EHR data. We provide benchmarking results using data from two real-world COVID-19 EHR datasets. One dataset is publicly available without needing any inquiry and another dataset can be accessed on request. We provide fair, reproducible benchmarking results for two tasks. We deploy all experiment results and models on an online platform. We also allow clinicians and researchers to upload their data to the platform and get quick prediction results using our trained models. We hope our efforts can further facilitate deep learning and machine learning research for COVID-19 predictive modeling.

Many real-world recognition problems are characterized by long-tailed label distributions. These distributions make representation learning highly challenging due to limited generalization over the tail classes. If the test distribution differs from the training distribution, e.g. uniform versus long-tailed, the problem of the distribution shift needs to be addressed. A recent line of work proposes learning multiple diverse experts to tackle this issue. Ensemble diversity is encouraged by various techniques, e.g. by specializing different experts in the head and the tail classes. In this work, we take an analytical approach and extend the notion of logit adjustment to ensembles to form a Balanced Product of Experts (BalPoE). BalPoE combines a family of experts with different test-time target distributions, generalizing several previous approaches. We show how to properly define these distributions and combine the experts in order to achieve unbiased predictions, by proving that the ensemble is Fisher-consistent for minimizing the balanced error. Our theoretical analysis shows that our balanced ensemble requires calibrated experts, which we achieve in practice using mixup. We conduct extensive experiments and our method obtains new state-of-the-art results on three long-tailed datasets: CIFAR-100-LT, ImageNet-LT, and iNaturalist-2018. Our code is available at https://github.com/emasa/BalPoE-CalibratedLT.

This paper presents an extended version of Deeper, a search-based simulation-integrated test solution that generates failure-revealing test scenarios for testing a deep neural network-based lane-keeping system. In the newly proposed version, we utilize a new set of bio-inspired search algorithms, genetic algorithm (GA), $({\mu}+{\lambda})$ and $({\mu},{\lambda})$ evolution strategies (ES), and particle swarm optimization (PSO), that leverage a quality population seed and domain-specific cross-over and mutation operations tailored for the presentation model used for modeling the test scenarios. In order to demonstrate the capabilities of the new test generators within Deeper, we carry out an empirical evaluation and comparison with regard to the results of five participating tools in the cyber-physical systems testing competition at SBST 2021. Our evaluation shows the newly proposed test generators in Deeper not only represent a considerable improvement on the previous version but also prove to be effective and efficient in provoking a considerable number of diverse failure-revealing test scenarios for testing an ML-driven lane-keeping system. They can trigger several failures while promoting test scenario diversity, under a limited test time budget, high target failure severity, and strict speed limit constraints.

Naftali Bennett spoke exclusively with Fox News Digital about the benefits of AI and the need to set parameters for its use now. The new drone swarm test conducted by the U.S. and its allies last week shows some of the wider applications of artificial intelligence (AI) in military settings while also raising some potential issues about how multiple militaries will be able to cooperate. "Just like coordination is needed to conduct classic, joint and coalition maneuvers and military operations, similar clear definitions of boundaries, tasks, responsibility and authority are needed to control and de-conflict drone swarms," retired Brig. Gen. Uri Engelhard, AI and cyber expert, member of the Israel Defense and Security Forum, told Fox News Digital. "If planned and conducted properly, the deployment of drone swarms should not be more challenging than other military activities."